Search

Unmanned aerial vehicles (UAVs) are effective tools for identifying road anomalies with limited detection coverage due to the discrete spatial distribution of roads. Despite computational, storage, and transmission challenges, existing detection algorithms can be improved to support this task with robustness and efficiency. In this study, the K-means clustering algorithm was used to calculate the best prior anchor boxes; Faster R-CNN (region-based convolutional neural network), YOLOX-s (You Only Look Once version X-small), YOLOv5-s, YOLOv7-tiny, YOLO-MobileNet, and YOLO-RDD models were built based on image data collected by UAVs. YOLO-MobileNet has the most lightweight model but performed worst in accuracy, but greatly reduces detection accuracy. YOLO-RDD (road distress detection) performed best with a mean average precision (mAP) of 0.701 above the Intersection over Union (IoU) value of 0.5 and achieved relatively high accuracy in detecting all four types of distress. The YOLO-RDD model most successfully detected potholes with an AP of 0.790. Significant or severe distresses were better identified, and minor cracks were relatively poorly identified. The YOLO-RDD model achieved an 85% computational reduction compared to YOLOv7-tiny while maintaining high detection accuracy. [ABSTRACT FROM AUTHOR]

Abstract Accurate estimates of fishing effort are necessary in order to assess interactions with the wider ecosystem and for defining and implementing appropriate management. In intertidal and inshore fisheries in which vessel monitoring systems (VMS) or logbook programmes may not be implemented, quantifying the distribution and intensity of fishing can be difficult. The most obvious effects of bottom-contact fishing are often physical changes to the habitat, such as scarring of the sediment following dredging or trawling. We explored the potential of applying remote sensing techniques to aerial imagery collected by an unmanned aerial vehicle, or drone, in an area of intertidal mud flat (0.52 km2) in Poole Harbour, UK, where shellfish dredging is widely carried out and conflicts between commercial fishing interests and the conservation of internationally important shorebird populations are a concern. Image classification and image texture analysis were performed on imagery collected during the open dredge season in November 2015, in order to calculate measures of fishing intensity across three areas of the harbour subject to different management measures. We found a significant correlation between results of the image texture analysis and official sightings records collected during the dredging season, indicating that this method most accurately quantified dredging disturbance. The relationship between shorebird densities and food intake rates and the results of this analysis method were then investigated to assess the potential for using remotely sensed measures of fishing effort to assess responses of overwintering shorebird populations to intertidal shellfish dredging. Our work highlights the application of such methods, providing a low-cost tool for quantifying fishing effort and predicting wildlife conflicts. Highlights • Two remote sensing techniques were used to quantify intertidal bottom contact fishing effort. • Results of unsupervised image classification and image texture analysis were not comparable. • Image texture analysis more accurately quantifies intertidal fishing effort. • The relationship between results of each method and shorebird feeding ecology are investigated. [ABSTRACT FROM AUTHOR]

In organic farming, clover is an important basis for green manure in crop rotation systems due to its nitrogen-fixing effect. However, clover is often sown in mixtures with grass to achieve a yield-increasing effect. In order to determine the quantity and distribution of clover and its influence on the subsequent crops, clover plants must be identified at the individual plant level and spatially differentiated from grass plants. In practice, this is usually done by visual estimation or extensive field sampling. High-resolution unmanned aerial vehicles (UAVs) offer a more efficient alternative. In the present study, clover and grass plants were classified based on spectral information from high-resolution UAV multispectral images and texture features using a random forest classifier. Three different timestamps were observed in order to depict the phenological development of clover and grass distributions. To reduce data redundancy and processing time, relevant texture features were selected based on a wrapper analysis and combined with the original bands. Including these texture features, a significant improvement in classification accuracy of up to 8% was achieved compared to a classification based on the original bands only. Depending on the phenological stage observed, this resulted in overall accuracies between 86% and 91%. Subsequently, high-resolution UAV imagery data allow for precise management recommendations for precision agriculture with site-specific fertilization measures. [ABSTRACT FROM AUTHOR]

Maize, an important cereal crop and crucial industrial material, is widely used in various fields, including food, feed, and industry. Maize is also a highly adaptable crop, capable of thriving under various climatic and soil conditions. Against the backdrop of intensified climate change, studying the classification of maize growth stages can aid in adjusting planting strategies to enhance yield and quality. Accurate classification of the growth stages of maize breeding materials is important for enhancing yield and quality in breeding endeavors. Traditional remote sensing-based crop growth stage classifications mainly rely on time series vegetation index (VI) analyses; however, VIs are prone to saturation under high-coverage conditions. Maize phenotypic traits at different growth stages may improve the accuracy of crop growth stage classifications. Therefore, we developed a method for classifying maize growth stages during the vegetative growth phase by combining maize phenotypic traits with different classification algorithms. First, we tested various VIs, texture features (TFs), and combinations of VI and TF as input features to estimate the leaf chlorophyll content (LCC), leaf area index (LAI), and fractional vegetation cover (FVC). We determined the optimal feature inputs and estimation methods and completed crop height (CH) extraction. Then, we tested different combinations of maize phenotypic traits as input variables to determine their accuracy in classifying growth stages and to identify the optimal combination and classification method. Finally, we compared the proposed method with traditional growth stage classification methods based on remote sensing VIs and machine learning models. The results indicate that (1) when the VI+TFs are used as input features, random forest regression (RFR) shows a good estimation performance for the LCC (R2: 0.920, RMSE: 3.655 SPAD units, MAE: 2.698 SPAD units), Gaussian process regression (GPR) performs well for the LAI (R2: 0.621, RMSE: 0.494, MAE: 0.397), and linear regression (LR) exhibits a good estimation performance for the FVC (R2: 0.777, RMSE: 0.051, MAE: 0.040); (2) when using the maize LCC, LAI, FVC, and CH phenotypic traits to classify maize growth stages, the random forest (RF) classification method achieved the highest accuracy (accuracy: 0.951, precision: 0.951, recall: 0.951, F1: 0.951); and (3) the effectiveness of the growth stage classification based on maize phenotypic traits outperforms that of traditional remote sensing-based crop growth stage classifications. [ABSTRACT FROM AUTHOR]

Multispectral remote sensing data with abundant spectral information can be used to compute vegetation indices to improve the accuracy of Ginkgo biloba yield prediction. The limited spatial resolution of multispectral cameras restricts the detail capture over wide farmland, but super-resolution (SR) reconstruction methods can enhance image quality. However, most existing SR models have been trained on images processed from downsampled high-resolution (HR) images, making them less effective in reconstructing real low-resolution (LR) images. This study proposes a GAN-based super-resolution reconstruction method (RMSRGAN) for multispectral remote sensing images of Ginkgo biloba trees in real scenes. A U-Net-based network is employed instead of the traditional discriminator. Convolutional block attention modules (CBAMs) are incorporated into the Residual-in-Residual Dense Blocks (RRDBs) of the generator and the U-Net of the discriminator to preserve image details and texture features. An unmanned aerial vehicle (UAV) equipped with a multispectral camera was employed to capture field multispectral remote sensing images of Ginkgo biloba trees at different spatial resolutions. Four matching HR and LR datasets were created from these images to train RMSRGAN. The proposed model outperforms the traditional models by achieving superior results in both quantitative evaluation metrics (peak signal-to-noise ratio (PSNR) is 32.490, 31.085, 27.084, 26.819, and structural similarity index (SSIM) is 0.894, 0.881, 0.832, 0.818, respectively) and qualitative evaluation visualization. Furthermore, the efficiency of our proposed method was tested by generating individual vegetation indices (VIs) from images taken before and after reconstruction to predict the yield of Ginkgo biloba. The results show that the SR images exhibit better R 2 and R M S E values than LR images. These findings show that RMSRGAN can improve the spatial resolution of real multispectral images, increasing the accuracy of Ginkgo biloba yield prediction and providing more effective and accurate data support for crop management. [ABSTRACT FROM AUTHOR]

This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods. [ABSTRACT FROM AUTHOR]

Introduction: The cold stress is one of the most important factors for affecting production throughout year, so effectively evaluating frost damage is great significant to the determination of the frost tolerance in lettuce. Methods: We proposed a high-throughput method to estimate lettuce FDI based on remote sensing. Red-Green-Blue (RGB) and multispectral images of open-field lettuce suffered from frost damage were captured by Unmanned Aerial Vehicle platform. Pearson correlation analysiswas employed to select FDIsensitive features from RGB and multispectral images. Then the models were established for different FDI-sensitive features based on sensor types and different groups according to lettuce colors using multiple linear regression, support vector machine and neural network algorithms, respectively. Results and discussion: Digital number of blue and red channels, spectral reflectance at blue, red and near-infrared bands as well as six vegetation indexes (VIs) were found to be significantly related to the FDI of all lettuce groups. The high sensitivity of four modified VIs to frost damage of all lettuce groups was confirmed. The average accuracy of models were improved by 3% to 14% through a combination of multisource features. Color of lettuce had a certain impact on the monitoring of frost damage by FDI prediction models, because the accuracy of models based on green lettuce groupwere generally higher. The MULTISURCE-GREEN-NN model with R² of 0.715 and RMSE of 0.014 had the best performance, providing a high-throughput and efficient technical tool for frost damage investigation which will assist the identification of cold-resistant green lettuce germplasm and related breeding. [ABSTRACT FROM AUTHOR]

Accurate estimates of canopy structure like canopy cover (CC), Leaf Area Index (LAI), crown volume (Vcr), as well as tree and stand structure like stem volume (V_st) and basal area (G), are considered essential measures to manage poplar plantations effectively as they are correlated with the growth rate and the detection of possible stress. This research exploits the possibility of developing a precision forestry application using an unmanned aerial vehicle (UAV), terrestrial digital camera and traditional field measurements to monitor poplar plantation variables. We set up the procedure using explanatory variables from the Grey Level Co-occurrence Matrix textural metrics (Entropy, Variance, Dissimilarity and Contrast) calculated based on UAV multispectral imagery. Our results show that the GCLM texture derived by multispectral ortomosaic provides adequate explanatory variables to predict poplar plantation characteristics related to plants' canopy and stand structure. The evaluation of the models targeting the different poplar plantation variables (i.e. Vcr, G_ha, Vst_ha, CC and LAI) with the four GLCM explanatory variables (i.e. Entropy, Variance, Dissimilarity and Contrast) consistently higher or equal resulted to R² ≥0.86. [ABSTRACT FROM AUTHOR]

The Leaf Area Index (LAI) is a crucial indicator of crop photosynthetic potential, which is of great significance in farmland monitoring and precision management. This study aimed to predict potato plant LAI for potato plant growth monitoring, integrating spectral, textural, and morphological data through UAV images and machine learning. A new texture index named VITs was established by fusing multi-channel information. Vegetation growth features (Vis and plant height Hdsm) and texture features (TIs and VITs) were obtained from drone digital images. Various feature combinations (VIs, VIs + TIs, VIs + VITs, VIs + VITs + Hdsm) in three growth stages were adopted to monitor potato plant LAI using Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), random forest (RF), and eXtreme gradient boosting (XGBoost), so as to find the best feature combinations and machine learning method. The performance of the newly built VITs was tested. Compared with traditional TIs, the estimation accuracy was obviously improved for all the growth stages and methods, especially in the tuber-growth stage using the RF method with 13.6% of R2 increase. The performance of Hdsm was verified by including it either as one input feature or not. Results showed that Hdsm could raise LAI estimation accuracy in every growth stage, whichever method is used. The most significant improvement appeared in the tuber-formation stage using SVR, with an 11.3% increase of R2. Considering both the feature combinations and the monitoring methods, the combination of VIs + VITs + Hdsm achieved the best results for all the growth stages and simulation methods. The best fitting of LAI in tuber-formation, tuber-growth, and starch-accumulation stages had an R2 of 0.92, 0.83, and 0.93, respectively, using the XGBoost method. This study showed that the combination of different features enhanced the simulation of LAI for multiple growth stages of potato plants by improving the monitoring accuracy. The method presented in this study can provide important references for potato plant growth monitoring. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV)-based remote sensing has been widely considered recently in field scale crop yield estimation. In this research, the capability of 13 spectral indices in the form of 5 groups was studied under different irrigation water and N fertilizer managements in terms of corn biomass monitoring and estimation. Farm experiments were conducted at Urmia University, Iran. The research was done using a randomized complete block design at three levels of 60, 80, and 100% of irrigation water and nitrogen requirements during four replications. The aerial imagery operations were performed using a fixed-wing UAV equipped with a Sequoia sensor during three plant growth stages including stem elongation, flowering, and silking. The effect of different irrigation water and nitrogen levels on vegetation indices and crop biomass was examined using variance decomposition analysis. Then, the correlation of the vegetation indices with corn biomass was evaluated by fitting linear regression models. Based on the obtained results, the indices based on near infrared (NIR) and red-edge spectral bands showed a better performance. Thus, the MERIS terrestrial chlorophyll index (MTCI) indicated the highest accuracy at estimating corn biomass during the growing season with the R2 and RMSE values of 0.92 and 8.27 ton/ha, respectively. Finally, some Bayesian model averaging (BMA) models were proposed to estimate corn biomass based on the selected indices and different spectral bands. Results of the BMA models revealed that the accuracy of biomass estimation models could be improved using the capabilities and advantages of different vegetation indices. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles have large prospects for organizing territory monitoring. To integrate them into this sphere, it is necessary to improve their high functionality and safety. Computer vision is one of the vital monitoring aspects. In this paper, we developed and validated a methodology for terrain classification. The overall classification procedure consists of the following steps: (1) pre-processing, (2) feature extraction, and (3) classification. For the pre-processing stage, a clustering method based on particle swarm optimization was elaborated, which helps to extract object patterns from the image. Feature extraction is conducted via Gray-Level Co-Occurrence Matrix calculation, and the output of the matrix is turned into the input for a feed-forward neural network classification stage. The developed computer vision system showed 88.7% accuracy on the selected test set. These results can provide high quality territory monitoring; prospectively, we plan to establish a self-positioning system based on computer vision. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV) low-altitude remote sensing technology has recently been adopted in China. However, mapping accuracy and production processes of true digital orthophoto maps (TDOMs) generated by UAV images require further improvement. In this study, ground control points were distributed and images were collected using a multi-rotor UAV and professional camera, at a flight height of 160 m above the ground and a designed ground sample distance (GSD) of 0.016 m. A structure from motion (SfM), revised digital surface model (DSM) and multi-view image texture compensation workflow were outlined to generate a high-precision TDOM. We then used randomly distributed checkpoints on the TDOM to verify its precision. The horizontal accuracy of the generated TDOM was 0.0365 m, the vertical accuracy was 0.0323 m, and the GSD was 0.0166 m. Tilt and shadowed areas of the TDOM were eliminated so that buildings maintained vertical viewing angles. This workflow produced a TDOM accuracy within 0.05 m, and provided an effective method for identifying rural homesteads, as well as land planning and design. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV) oblique photography technology has been applied more and more widely for the 3D reconstruction of real-scene models due to its high efficiency and low cost. However, there are many kinds of UAVs with different positioning methods, camera models, and resolutions. To evaluate the performance levels of different types of UAVs in terms of their application to 3D reconstruction, this study took a primary school as the research area and obtained image information through oblique photography of four UAVs of different levels at different flight altitudes. We then conducted a comparative analysis of the accuracy of their 3D reconstruction models. The results show that the 3D reconstruction model of M300RTK has the highest dimensional accuracy, with an error of about 1.1–1.4 m per kilometer, followed by M600Pro (1.5–3.6 m), Inspire2 (1.8–4.2 m), and Phantom4Pro (2.4–5.6 m), but the accuracy of the 3D reconstruction model was found to have no relationship with the flight altitude. At the same time, the resolution of the 3D reconstruction model improved as the flight altitude decreased and the image resolution of the PTZ camera increased. The 3D reconstruction model resolution of the M300RTK + P1 camera was the highest. For every 10 m decrease in flight altitude, the clarity of the 3D reconstruction model improved by 16.81%. The UAV flight time decreased as the UAV flying altitude increased, and the time required for 3D reconstruction of the model increased obviously as the number and resolution of photos increased. [ABSTRACT FROM AUTHOR]

The latest technological advances in space-borne imagery have significantly enhanced the acquisition of high-quality data. With the availability of very high-resolution satellites, such as Pléiades, it is now possible to estimate tree parameters at the individual level with high fidelity. Despite innovative advantages on high-precision satellites, data acquisition is not yet available to the public at a reasonable cost. Unmanned aerial vehicles (UAVs) have the practical advantage of data acquisition at a higher spatial resolution than that of satellites. This study is divided into two main parts: (1) we describe the estimation of basic tree attributes, such as tree height, crown diameter, diameter at breast height (DBH), and stem volume derived from UAV data based on structure from motion (SfM) algorithms; and (2) we consider the extrapolation of the UAV data to a larger area, using correlation between satellite and UAV observations as an economically viable approach. Results have shown that UAVs can be used to predict tree characteristics with high accuracy (i.e., crown projection, stem volume, cross-sectional area (CSA), and height). We observed a significant relation between extracted data from UAV and ground data with R2 = 0.71 for stem volume, R2 = 0.87 for height, and R2 = 0.60 for CSA. In addition, our results showed a high linear relation between spectral data from the UAV and the satellite (R2 = 0.94). Overall, the accuracy of the results between UAV and Pléiades was reasonable and showed that the used methods are feasible for extrapolation of extracted data from UAV to larger areas. [ABSTRACT FROM AUTHOR]

The multiple protocols that have been developed to characterize river hydromorphology, partly in response to legislative drivers such as the European Union Water Framework Directive (EU WFD), make the comparison of results obtained in different countries challenging. Recent studies have analyzed the comparability of existing methods, with remote sensing based approaches being proposed as a potential means of harmonizing hydromorphological characterization protocols. However, the resolution achieved by remote sensing products may not be sufficient to assess some of the key hydromorphological features that are required to allow an accurate characterization. Methodologies based on high resolution aerial photography taken from Unmanned Aerial Vehicles (UAVs) have been proposed by several authors as potential approaches to overcome these limitations. Here, we explore the applicability of an existing UAV based framework for hydromorphological characterization to three different fluvial settings representing some of the distinct ecoregions defined by the WFD geographical intercalibration groups (GIGs). The framework is based on the automated recognition of hydromorphological features via tested and validated Artificial Neural Networks (ANNs). Results show that the framework is transferable to the Central-Baltic and Mediterranean GIGs with accuracies in feature identification above 70%. Accuracies of 50% are achieved when the framework is implemented in the Very Large Rivers GIG. The framework successfully identified vegetation, deep water, shallow water, riffles, side bars and shadows for the majority of the reaches. However, further algorithm development is required to ensure a wider range of features (e.g., chutes, structures and erosion) are accurately identified. This study also highlights the need to develop an objective and fit for purpose hydromorphological characterization framework to be adopted within all EU member states to facilitate comparison of results. [ABSTRACT FROM AUTHOR]

This paper presents a method for mosaicking unmanned aerial vehicle (UAV) multispectral images. The main purpose of the proposed method is to reduce spatial distortion in the mosaicking process and increase robustness and the speed of the operation. Most UAV multispectral images have multiple bands, and in every band, ground targets have a variety of reflection characteristics that will result in diverse feature quality for feature matching. In this research, an information entropy-based evaluation method is used to select the optimal band for feature matching among the UAV images. To produce more robust matching results for the following alignment step, the evaluation method takes the contrast and spatial distribution of the feature points into consideration at the same time. In most common image mosaicking processes, the digital orthophoto map (DOM) is generated to achieve maximum spatial accuracy. During this process, the original image data will experience considerable irregular resampling, and the process is also unstable in some circumstances. The alignment step uses a simplified projection model that treats the ground as planar is provided, by which the alignment parameters are applied directly to the images instead of generating 3D points, to avoid irregular resampling and unstable 3D reconstruction. The proposed method is proved to be more efficient and accurate and has lower spectral distortion than state-of-the-art mosaicking software. [ABSTRACT FROM AUTHOR]

The use of Unmanned Aerial Vehicles (UAV) for photogrammetric surveying has recently gained enormous popularity. Images taken from UAVs are used for generating Digital Surface Models (DSMs) and orthorectified images. In the glaciological context, these can serve for quantifying ice volume change or glacier motion. This study focuses on the accuracy of UAV-derived DSMs. In particular, we analyze the influence of the number and disposition of Ground Control Points (GCPs) needed for georeferencing the derived products. A total of 1321 different DSMs were generated from eight surveys distributed on three glaciers in the Swiss Alps during winter, summer and autumn. The vertical and horizontal accuracy was assessed by cross-validation with thousands of validation points measured with a Global Positioning System. Our results show that the accuracy increases asymptotically with increasing number of GCPs until a certain density of GCPs is reached. We call this the optimal GCP density. The results indicate that DSMs built with this optimal GCP density have a vertical (horizontal) accuracy ranging between 0.10 and 0.25m (0.03 and 0.09 m) across all datasets. In addition, the impact of the GCP distribution on the DSM accuracy was investigated. The local accuracy of a DSM decreases when increasing the distance to the closest GCP, typically at a rate of 0.09m per 100-m distance. The impact of the glacier's surface texture (ice or snow) was also addressed. The results show that besides cases with a surface covered by fresh snow, the surface texture does not significantly influence the DSM accuracy. [ABSTRACT FROM AUTHOR]

Vessel maintenance requires periodic visual inspection of the hull in order to detect typical defective situations of steel structures such as, among others, coating breakdown and corrosion. These inspections are typically performed by well-trained surveyors at great cost because of the need for providing access means (e.g., scaffolding and/or cherry pickers) that allow the inspector to be at arm's reach from the structure under inspection. This paper describes a defect detection approach comprising a micro-aerial vehicle which is used to collect images from the surfaces under inspection, particularly focusing on remote areas where the surveyor has no visual access, and a coating breakdown/corrosion detector based on a three-layer feed-forward artificial neural network. As it is discussed in the paper, the success of the inspection process depends not only on the defect detection software but also on a number of assistance functions provided by the control architecture of the aerial platform, whose aim is to improve picture quality. Both aspects of the work are described along the different sections of the paper, as well as the classification performance attained. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV) low-altitude remote sensing technology has recently been adopted in China. However, mapping accuracy and production processes of true digital orthophoto maps (TDOMs) generated by UAV images require further improvement. In this study, ground control points were distributed and images were collected using a multi-rotor UAV and professional camera, at a flight height of 160 m above the ground and a designed ground sample distance (GSD) of 0.016 m. A structure from motion (SfM), revised digital surface model (DSM) and multi-view image texture compensation workflow were outlined to generate a high-precision TDOM. We then used randomly distributed checkpoints on the TDOM to verify its precision. The horizontal accuracy of the generated TDOM was 0.0365 m, the vertical accuracy was 0.0323 m, and the GSD was 0.0166 m. Tilt and shadowed areas of the TDOM were eliminated so that buildings maintained vertical viewing angles. This workflow produced a TDOM accuracy within 0.05 m, and provided an effective method for identifying rural homesteads, as well as land planning and design.

Shrublands are the main vegetation component in the Gobi region and contribute considerably to its ecosystem. Accurately classifying individual shrub vegetation species to understand their spatial distributions and to effectively monitor species diversity in the Gobi ecosystem is essential. High-resolution remote sensing data create vegetation type inventories over large areas. However, high spectral similarity between shrublands and surrounding areas remains a challenge. In this study, we provide a case study that integrates object-based image analysis (OBIA) and the random forest (RF) model to classify shrubland species automatically. The Gobi region on the southern slope of the Tian Shan Mountains in Northwest China was analyzed using readily available unmanned aerial vehicle (UAV) RGB imagery (1.5 cm spatial resolution). Different spectral and texture index images were derived from UAV RGB images as variables for species classification. Principal component analysis (PCA) extracted features from different types of variable sets (original bands, original bands + spectral indices, and original bands + spectral indices + texture indices). We tested the ability of several non-parametric decision tree models and different types of variable sets to classify shrub species. Moreover, we analyzed three main shrubland areas comprising different shrub species and compared the prediction accuracies of the optimal model in combination with different types of variable sets. We found that the RF model could generate higher accuracy compared with the other two models. The best results were obtained using a combination of the optimal variable set and the RF model with an 88.63% overall accuracy and 0.82 kappa coefficient. Integrating OBIA and RF in the species classification process provides a promising method for automatic mapping of individual shrub species in the Gobi region and can reduce the workload of individual shrub species classification. [ABSTRACT FROM AUTHOR]

The Kobresia pygmaea (KP) community is a key succession stage of alpine meadow degradation on the Qinghai–Tibet Plateau (QTP). However, most of the grassland classification and mapping studies have been performed at the grassland type level. The spatial distribution and impact factors of KP on the QTP are still unclear. In this study, field measurements of the grassland vegetation community in the eastern part of the QTP (Counties of Zeku, Henan and Maqu) from 2015 to 2019 were acquired using unmanned aerial vehicle (UAV) technology. The machine learning algorithms for grassland vegetation community classification were constructed by combining Gaofen satellite images and topographic indices. Then, the spatial distribution of KP community was mapped. The results showed that: (1) For all field observed sites, the alpine meadow vegetation communities demonstrated a considerable spatial heterogeneity. The traditional classification methods can hardly distinguish those communities due to the high similarity of their spectral characteristics. (2) The random forest method based on the combination of satellite vegetation indices, texture feature and topographic indices exhibited the best performance in three counties, with overall accuracy and Kappa coefficient ranged from 74.06% to 83.92% and 0.65 to 0.80, respectively. (3) As a whole, the area of KP community reached 1434.07 km2, and accounted for 7.20% of the study area. We concluded that the combination of satellite remote sensing, UAV surveying and machine learning can be used for KP classification and mapping at community level. [ABSTRACT FROM AUTHOR]

By combining the spectral and texture features of images captured by unmanned aerial vehicles (UAVs), the accurate and timely detection of wheat Fusarium head blight (FHB) can be realized. This study presents a methodology to select the optimal window size of the gray-level co-occurrence matrix (GLCM) to extract texture features from UAV images for FHB detection. Host conditions and the disease distribution were combined to construct the model, and its overall accuracy, sensitivity, and generalization ability were evaluated. First, the sensitive spectral features and bands of the UAV-derived hyperspectral images were obtained, and then texture features were selected. Subsequently, spectral features and texture features extracted from windows of different sizes were input to classify the area of severe FHB. According to the model comparison, the optimal window size was obtained. With the collinearity between features eliminated, the best performance of the logistic model reached, with an accuracy, F1 score, and area under the receiver operating characteristic curve of 0.90, 0.79, and 0.79, respectively, when the window size of the GLCM was 5 × 5 pixels on May 3, and of 0.90, 0.83, and 0.82, respectively, when the size was 17 × 17 pixels on May 8. The results showed that the selection of an appropriate GLCM window size for texture feature extraction enabled more accurate disease detection. [ABSTRACT FROM AUTHOR]

Although textural information can be used to estimate vegetation biomass, its use for estimating crop biomass is rare, and previous methods lacked a mechanistic explanation for the relationship to biomass. The objective of the present study was to develop mechanistic textural indices for estimating cotton biomass and solving saturation problems at medium and high biomass levels. A nitrogen (N) fertilization experiment was established, and unmanned aerial vehicle optical images and field measured biomass data were obtained during critical cotton growth stages. Based on these data, two textural indices, namely the normalized difference texture index combining contrast and the inverse difference moment of the green band (NBTI (CON, IDM)g) and normalized difference texture index combining entropy and the inverse difference moment of the green band (NBTI (ENT, IDM)g), were proposed by analyzing the mechanism of texture parameters for biomass prediction and the law of texture parameters changing with biomass. These indices were compared with spectral indices commonly used for biomass estimation using independent validation data, such as the normalized difference vegetation index (NDVI). The results showed that the proposed textural indices performed better than the spectral indices with no saturation problems occurring. The combination of spectral and textural indices using a stepwise regression method performed better for biomass estimation than using only spectral or textural indices. This method has considerable potential for improving the accuracy of biomass estimations for the subsequent delineation of precise cotton management zones. [ABSTRACT FROM AUTHOR]

Predicting the crop nitrogen (N) nutrition status is critical for optimizing nitrogen fertilizer application. The present study examined the ability of multiple image features derived from unmanned aerial vehicle (UAV) RGB images for winter wheat N status estimation across multiple critical growth stages. The image features consisted of RGB-based vegetation indices (VIs), color parameters, and textures, which represented image features of different aspects and different types. To determine which N status indicators could be well-estimated, we considered two mass-based N status indicators (i.e., the leaf N concentration (LNC) and plant N concentration (PNC)) and two area-based N status indicators (i.e., the leaf N density (LND) and plant N density (PND)). Sixteen RGB-based VIs associated with crop growth were selected. Five color space models, including RGB, HSV, L*a*b*, L*c*h*, and L*u*v*, were used to quantify the winter wheat canopy color. The combination of Gaussian processes regression (GPR) and Gabor-based textures with four orientations and five scales was proposed to estimate the winter wheat N status. The gray level co-occurrence matrix (GLCM)-based textures with four orientations were extracted for comparison. The heterogeneity in the textures of different orientations was evaluated using the measures of mean and coefficient of variation (CV). The variable importance in projection (VIP) derived from partial least square regression (PLSR) and a band analysis tool based on Gaussian processes regression (GPR-BAT) were used to identify the best performing image features for the N status estimation. The results indicated that (1) the combination of RGB-based VIs or color parameters only could produce reliable estimates of PND and the GPR model based on the combination of color parameters yielded a higher accuracy for the estimation of PND (R2val = 0.571, RMSEval = 2.846 g/m2, and RPDval = 1.532), compared to that based on the combination of RGB-based VIs; (2) there was no significant heterogeneity in the textures of different orientations and the textures of 45 degrees were recommended in the winter wheat N status estimation; (3) compared with the RGB-based VIs and color parameters, the GPR model based on the Gabor-based textures produced a higher accuracy for the estimation of PND (R2val = 0.675, RMSEval = 2.493 g/m2, and RPDval = 1.748) and the PLSR model based on the GLCM-based textures produced a higher accuracy for the estimation of PNC (R2val = 0.612, RMSEval = 0.380%, and RPDval = 1.601); and (4) the combined use of RGB-based VIs, color parameters, and textures produced comparable estimation results to using textures alone. Both VIP-PLSR and GPR-BAT analyses confirmed that image textures contributed most to the estimation of winter wheat N status. The experimental results reveal the potential of image textures derived from high-definition UAV-based RGB images for the estimation of the winter wheat N status. They also suggest that a conventional low-cost digital camera mounted on a UAV could be well-suited for winter wheat N status monitoring in a fast and non-destructive way. [ABSTRACT FROM AUTHOR]

Quantifying crop residue cover (CRC) on field surfaces is important for monitoring the tillage intensity and promoting sustainable management. Remote-sensing-based techniques have proven practical for determining CRC, however, the methods used are primarily limited to empirical regression based on crop residue indices (CRIs). This study provides a systematic evaluation of empirical regressions and machine learning (ML) algorithms based on their ability to estimate CRC using Sentinel-2 Multispectral Instrument (MSI) data. Unmanned aerial vehicle orthomosaics were used to extracted ground CRC for training Sentinel-2 data-based CRC models. For empirical regression, nine MSI bands, 10 published CRIs, three proposed CRIs, and four mean textural features were evaluated using univariate linear regression. The best performance was obtained by a three-band index calculated using (B2 − B4)/(B2 − B12), with an R2cv of 0.63 and RMSEcv of 6.509%, using a 10-fold cross-validation. The methodologies of partial least squares regression (PLSR), artificial neural network (ANN), Gaussian process regression (GPR), support vector regression (SVR), and random forest (RF) were compared with four groups of predictors, including nine MSI bands, 13 CRIs, a combination of MSI bands and mean textural features, and a combination of CRIs and textural features. In general, ML approaches achieved high accuracy. A PLSR model with 13 CRIs and textural features resulted in an accuracy of R2cv = 0.66 and RMSEcv = 6.427%. An RF model with predictors of MSI bands and textural features estimated CRC with an R2cv = 0.61 and RMSEcv = 6.415%. The estimation was improved by an SVR model with the same input predictors (R2cv = 0.67, RMSEcv = 6.343%), followed by a GPR model based on CRIs and textural features. The performance of GPR models was further improved by optimal input variables. A GPR model with six input variables, three MSI bands and three textural features, performed the best, with R2cv = 0.69 and RMSEcv = 6.149%. This study provides a reference for estimating CRC from Sentinel-2 imagery using ML approaches. The GPR approach is recommended. A combination of spectral information and textural features leads to an improvement in the retrieval of CRC. [ABSTRACT FROM AUTHOR]

Background: Automated phenotyping technologies are continually advancing the breeding process. However, collecting various secondary traits throughout the growing season and processing massive amounts of data still take great efforts and time. Selecting a minimum number of secondary traits that have the maximum predictive power has the potential to reduce phenotyping efforts. The objective of this study was to select principal features extracted from UAV imagery and critical growth stages that contributed the most in explaining winter wheat grain yield. Five dates of multispectral images and seven dates of RGB images were collected by a UAV system during the spring growing season in 2018. Two classes of features (variables), totaling to 172 variables, were extracted for each plot from the vegetation index and plant height maps, including pixel statistics and dynamic growth rates. A parametric algorithm, LASSO regression (the least angle and shrinkage selection operator), and a non-parametric algorithm, random forest, were applied for variable selection. The regression coefficients estimated by LASSO and the permutation importance scores provided by random forest were used to determine the ten most important variables influencing grain yield from each algorithm. Results: Both selection algorithms assigned the highest importance score to the variables related with plant height around the grain filling stage. Some vegetation indices related variables were also selected by the algorithms mainly at earlier to mid growth stages and during the senescence. Compared with the yield prediction using all 172 variables derived from measured phenotypes, using the selected variables performed comparable or even better. We also noticed that the prediction accuracy on the adapted NE lines (r = 0.58–0.81) was higher than the other lines (r = 0.21–0.59) included in this study with different genetic backgrounds. Conclusions: With the ultra-high resolution plot imagery obtained by the UAS-based phenotyping we are now able to derive more features, such as the variation of plant height or vegetation indices within a plot other than just an averaged number, that are potentially very useful for the breeding purpose. However, too many features or variables can be derived in this way. The promising results from this study suggests that the selected set from those variables can have comparable prediction accuracies on the grain yield prediction than the full set of them but possibly resulting in a better allocation of efforts and resources on phenotypic data collection and processing. [ABSTRACT FROM AUTHOR]

The precise classification of crop types is an important basis of agricultural monitoring and crop protection. With the rapid development of unmanned aerial vehicle (UAV) technology, UAV-borne hyperspectral remote sensing imagery with high spatial resolution has become the ideal data source for the precise classification of crops. For precise classification of crops with a wide variety of classes and varied spectra, the traditional spectral-based classification method has difficulty in mining large-scale spatial information and maintaining the detailed features of the classes. Therefore, a precise crop classification method using spectral-spatial-location fusion based on conditional random fields (SSLF-CRF) for UAV-borne hyperspectral remote sensing imagery is proposed in this paper. The proposed method integrates the spectral information, the spatial context, the spatial features, and the spatial location information in the conditional random field model by the probabilistic potentials, providing complementary information for the crop discrimination from different perspectives. The experimental results obtained with two UAV-borne high spatial resolution hyperspectral images confirm that the proposed method can solve the problems of large-scale spatial information modeling and spectral variability, improving the classification accuracy for each crop type. This method has important significance for the precise classification of crops in hyperspectral remote sensing imagery. [ABSTRACT FROM AUTHOR]

The fine classification of crops is critical for food security and agricultural management. There are many different species of crops, some of which have similar spectral curves. As a result, the precise classification of crops is a difficult task. Although the classification methods that incorporate spatial information can reduce the noise and improve the classification accuracy, to a certain extent, the problem is far from solved. Therefore, in this paper, the method of spatial–spectral fusion based on conditional random fields (SSF-CRF) for the fine classification of crops in UAV-borne hyperspectral remote sensing imagery is presented. The proposed method designs suitable potential functions in a pairwise conditional random field model, fusing the spectral and spatial features to reduce the spectral variation within the homogenous regions and accurately identify the crops. The experiments on hyperspectral datasets of the cities of Hanchuan and Honghu in China showed that, compared with the traditional methods, the proposed classification method can effectively improve the classification accuracy, protect the edges and shapes of the features, and relieve excessive smoothing, while retaining detailed information. This method has important significance for the fine classification of crops in hyperspectral remote sensing imagery. [ABSTRACT FROM AUTHOR]