Search

Unmanned aerial vehicles (UAVs) have become a very popular way of acquiring video within contexts such as remote data acquisition or surveillance. Unfortunately, their viewpoint is often unstable, which tends to impact the automatic processing of their video flux negatively. To counteract the effects of an inconsistent viewpoint, two video processing strategies are classically adopted, namely registration and stabilization, which tend to be affected by distinct issues, namely jitter and drifting. Following our prior work, we suggest that the motion estimators used in both situations can be modeled to take into account their inherent errors. By acknowledging that drifting and jittery errors are of a different nature, we propose a combination that is able to limit their influence and build a hybrid solution for jitter-free video registration. In this work, however, our modeling was restricted to 2D-rigid transforms, which are rather limited in the case of airborne videos. In the present paper, we extend and refine the theoretical ground of our previous work. This addition allows us to show how to practically adapt our previous work to perspective transforms, which our study shows to be much more accurate for this problem. A lightweight implementation enables us to automatically register stationary UAV videos in real time. Our evaluation includes traffic surveillance recordings of up to 2 h and shows the potential of the proposed approach when paired with background subtraction tasks.

The computed tomography imaging spectrometer (CTIS) is a snapshot hyperspectral imaging system. Its output is a 2D image of multiplexed spatiospectral projections of the hyperspectral cube of the scene. Traditionally, the 3D cube is reconstructed from this image before further analysis. In this paper, we show that it is possible to learn information directly from the CTIS raw output, by training a neural network to perform binary classification on such images. The use case we study is an agricultural one, as snapshot imagery is used substantially in this field: the detection of apple scab lesions on leaves. To train the network appropriately and to study several degrees of scab infection, we simulated CTIS images of scabbed leaves. This was made possible with a novel CTIS simulator, where special care was taken to preserve realistic pixel intensities compared to true images. To the best of our knowledge, this is the first application of compressed learning on a simulated CTIS system.

The land cover reconstruction from monochromatic historical aerial images is a challenging task that has recently attracted an increasing interest from the scientific community with the proliferation of large-scale epidemiological studies involving retrospective analysis of spatial patterns. However, the efforts made by the computer vision community in remote-sensing applications are mostly focused on prospective approaches through the analysis of high-resolution multi-spectral data acquired by the advanced spatial programs. Hence, four contributions are proposed in this paper. They aim at providing a comparison basis for the future development of computer vision algorithms applied to the automation of the land cover reconstruction from monochromatic historical aerial images. First, a new multi-scale multi-date dataset composed of 4.9 million non-overlapping annotated patches of the France territory between 1970 and 1990 has been created with the help of geography experts. This dataset has been named HistAerial. Second, an extensive comparison study of the state-of-the-art texture features extraction and classification algorithms, including deep convolutional neural networks (DCNNs), has been performed. It is presented in the form of an evaluation. Third, a novel low-dimensional local texture filter named rotated-corner local binary pattern (R-CRLBP) is presented as a simplification of the binary gradient contours filter through the use of an orthogonal combination representation. Finally, a novel combination of low-dimensional texture descriptors, including the R-CRLBP filter, is introduced as a light combination of local binary patterns (LCoLBPs). The LCoLBP filter achieved state-of-the-art results on the HistAerial dataset while conserving a relatively low-dimensional feature vector space compared with the DCNN approaches (17 times shorter).

In this paper, we propose a comparative study of various segmentation methods applied to the extraction of tree leaves from natural images. This study follows the design of a mobile application, developed by Cerutti et al. (published in ReVeS Participation--Tree Species Classification Using Random Forests and Botanical Features. CLEF 2012), to highlight the impact of the choices made for segmentation aspects. All the tests are based on a database of 232 images of tree leaves depicted on natural background from smartphones acquisitions. We also propose to study the improvements, in terms of performance, using preprocessing tools, such as the interaction between the user and the application through an input stroke, as well as the use of color distance maps. The results presented in this paper shows that the method developed by Cerutti et al. (denoted Guided Active Contour), obtains the best score for almost all observation criteria. Finally, we detail our online benchmark composed of 14 unsupervised methods and 6 supervised ones.

Existing image analysis algorithms cannot achieve consistency with human visual classification results when classifying particles based on angular levels. To address this issue, this paper proposes an image analysis method based on triangle side ratio to quantify particle angularity, referred to as a TSR method. The proposed method utilizes a primary parameter, Mean Angularity, to assess the mean angularity level, and employs three auxiliary parameters to offer insights into the Sharpest Angularity, the Flat Proportion, and the Number of Angularity. When quantifying the angularity, the method further provides the count of convex angles. Each parameter can reflect different characteristic information of the angularity. When using the mean angularity level to order particles, the TSR method achieves the same results as visual classification, and furthermore introduces a range of values for the main parameter corresponding to the different angularity levels. The TSR method is simpler and more stable, since the particle parameters can be calculated directly without contour smoothing, and consistent results are achieved for different shapes with the same degree of angular sharpness. The results of the study on lunar soil, volcanic rock, mechanism stone, and stream stone, show that the TSR method can objectively and comprehensively analyze and quantify the particle angularity. [ABSTRACT FROM AUTHOR]

Downstream pebble variability in river systems is assessed through various methods, with recent emphasis on efficient, time-saving semi-automatic processes involving photography and digital analysis. The Inaouène valley, however, lacked a comprehensive survey of its main channel using either manual or image-based methods. This study bridges this gap by combining both approaches to analyze the downstream evolution of surface pebbles' morphometric parameters along approximately 60 km of the Inaouène's middle reach. Our research focuses on two key aspects: grain size and particle shape. Results reveal a general downstream trend of size fining, increasing circularity and decreasing elongation, primarily attributed to abrasion and travel distance. Notably, this pattern is interrupted by localized variations associated with tributary inputs and sediment recycling processes. This study significantly contributes to the understanding of fluvial sediment dynamics in the Inaouène Valley. Its findings have broad implications, supporting ecological assessment and restoration efforts, while also informing decision-making in river engineering and management. By providing a comprehensive analysis of pebble characteristics and their downstream evolution, this research establishes a foundation for future geomorphological studies and practical applications in river system management. [ABSTRACT FROM AUTHOR]

This study systematically reviews the integration of artificial intelligence (AI) and remote sensing technologies to address the issue of crop water stress caused by rising global temperatures and climate change; in particular, it evaluates the effectiveness of various non-destructive remote sensing platforms (RGB, thermal imaging, and hyperspectral imaging) and AI techniques (machine learning, deep learning, ensemble methods, GAN, and XAI) in monitoring and predicting crop water stress. The analysis focuses on variability in precipitation due to climate change and explores how these technologies can be strategically combined under data-limited conditions to enhance agricultural productivity. Furthermore, this study is expected to contribute to improving sustainable agricultural practices and mitigating the negative impacts of climate change on crop yield and quality. [ABSTRACT FROM AUTHOR]

Poland as well as other countries keep extensive collections of 20th and 21st-century aerial photos, which are underexploited compared to such other archival materials as satellite imagery. Meanwhile, they offer significant research potential in various areas, including urban development, land use changes, and long-term environmental monitoring. Archival photographs are detailed, often obtained every five to ten years, and feature high resolution, from 20 cm to 1 m. Their overlap can facilitate creating precise digital models that illustrate topography and land cover, which are essential variables in many scientific contexts. However, rapidly transforming these photographs into geographically accurate measurements of the Earth's surface poses challenges. This article explores the obstacles in automating the processing of historical photographs and presents the main scientific research directions associated with these images. Recent advancements in enhancing work˚ows, including the development of modern digital photogrammetry tools, algorithms, and machine learning techniques are also discussed. These developments are crucial for unlocking the full potential of aerial photographs, making them easier accessible and valuable for a broader range of scientific fields. These underutilized photographs are increasingly recognized as vital in various research domains due to technological advancements. Integrating new methods with these historical images offers unprecedented opportunities for scientific discovery and historical understanding, bridging the past with the future through innovative research techniques. [ABSTRACT FROM AUTHOR]

The interconnection between the objectives of territorial development and those of the agro-ecological transition highlights the value of past knowledge in the sustainable management of resources and agro-ecological systems. However, the lack of data creates difficulties for retrospection in rural areas. This paper contributes to the search for such knowledge from the past by developing an interactive methodology capable of combining heterogeneous information sources with the activation of local collective memory. Its effectiveness is based on ensuring the interoperability of information and communication in an environment simultaneously shaped by geoinformatics and 3D geovisualisations. This virtual environment fostered participation and interactivity, supported by representations of the paleo-landscape (Ottoman period). Furthermore, synergies were achieved between information sources, which were integrated into local spatial systems. The application example involved identifying a rice field that existed between the 15th and 19th centuries in Thessaly, Greece. It is an interesting case because the research results indicated that the location and organisation of the crop, combined with the spatio-temporal coordination required, ensured the sustainable use of natural resources. The interplay between information and communication facilitated community participation and the activation of its collective memory as an information source that enriched the search itself and local intelligence. [ABSTRACT FROM AUTHOR]

In this study, we propose a novel method for quantifying tortuosity in 3D voxelized objects. As a shape characteristic, tortuosity has been widely recognized as a valuable feature in image analysis, particularly in the field of medical imaging. Our proposed method extends the two-dimensional approach of the Slope Chain Code (SCC) which creates a one-dimensional representation of curves. The utility of 3D tortuosity ( τ 3 D ) as a shape descriptor was investigated by characterizing brain structures. The results of the τ 3 D computation on the central sulcus and the main lobes revealed significant differences between Alzheimer's disease (AD) patients and control subjects, suggesting its potential as a biomarker for AD. We found a p < 0.05 for the left central sulcus and the four brain lobes. [ABSTRACT FROM AUTHOR]

The task of tree species classification through deep learning has been challenging for the forestry community, and the lack of standardized datasets has hindered further progress. Our work presents a solution in the form of a large bark image dataset called CentralBark, which enhances the deep learning-based tree species classification. Additionally, we have laid out an efficient and repeatable data collection protocol to assist future works in an organized manner. The dataset contains images of 25 central hardwood and Appalachian region tree species, with over 19,000 images of varying diameters, light, and moisture conditions. We tested 25 species: elm, oak, American basswood, American beech, American elm, American sycamore, bitternut hickory, black cherry, black locust, black oak, black walnut, eastern cottonwood, hackberry, honey locust, northern red oak, Ohio buckeye, Osage-orange, pignut hickory, sassafras, shagbark hickory silver maple, slippery elm, sugar maple, sweetgum, white ash, white oak, and yellow poplar. Our experiment involved testing three different models to assess the feasibility of species classification using unaltered and uncropped images during the species-classification training process. We achieved an overall accuracy of 83.21% using the EfficientNet-b3 model, which was the best of the three models (EfficientNet-b3, ResNet-50, and MobileNet-V3-small), and an average accuracy of 80.23%. [ABSTRACT FROM AUTHOR]

In the last decade, many aerial photographic archives have started to be digitized for multiple purposes, including digital preservation and geoprocessing. This paper analyzes the effects of professional photogrammetric versus consumer-grade scanners on the processing of analog historical aerial photographs. An image block over Warsaw is considered, featuring 38 photographs acquired in 1986 (Wild RC10, Normal Aviogon II lens, 23 × 23 cm format) with a ground sampling distance (GSD) of 4 cm. Aerial triangulation (AT) and dense image matching (DIM) procedures are considered, analyzing how scanning modalities are important in the massive digitization of analog images for georeferencing and 3D product generation. The achieved results show how consumer-grade scanners, unlike more expensive photogrammetric scanners, do not possess adequate recording quality to ensure high accuracy and geometric precision for geoprocessing purposes. However, consumer-grade scanners can be used for time and cost-efficient applications where a partial loss of data quality is not critical. [ABSTRACT FROM AUTHOR]

This paper optimizes the 2D Wadell roundness calculation of particles based on digital image processing methods. An algorithm for grouping corner key points is proposed to distinguish each independent corner. Additionally, the cyclic midpoint filtering method is introduced for corner dealiasing, aiming to mitigate aliasing issues effectively. The relationships between the number of corner pixels (m), the central angle of the corner (α) and the parameter of the dealiasing degree (n) are established. The Krumbein chart and a sandstone thin section image were used as examples to calculate the 2D Wadell roundness. A set of regular shapes is calculated, and the error of this method is discussed. When α ≥ 30°, the maximum error of Wadell roundness for regular shapes is 5.21%; when 12° ≤ α < 30°, the maximum error increases. By applying interpolation to increase the corner pixels to the minimum number (m0) within the allowable range of error, based on the α-m0 relational expression obtained in this study, the error of the corner circle can be minimized. The results indicate that as the value of m increases, the optimal range interval for n also widens. Additionally, a higher value of α leads to a lower dependence on m. The study's results can be applied to dealiasing and shape analysis of complex closed contours. [ABSTRACT FROM AUTHOR]

Instream large wood (i.e., downed trees, branches and roots larger than 1 m in length and 10 cm diameter) has essential geopmorphological and ecological functions supporting the health of river ecosystems. Still, even though its transport during floods may pose a risk, it is rarely observed and, therefore, poorly understood. This paper presents a novel approach to detect pieces of instream wood from video. The approach uses a Convolutional Neural Network to detect wood automatically. We sampled data to represent different wood transport conditions, combining 20 datasets to yield thousands of instream wood images. We designed multiple scenarios using different data subsets with and without data augmentation and analyzed the contribution of each one to the effectiveness of the model using k-fold cross-validation. The mean average precision of the model varies between 35 and 93 percent, and is highly influenced by the quality of the data which it detects. When the image resolution is low, the identified components in the labeled pieces, rather than exhibiting distinct characteristics such as bark or branches, appear more akin to amorphous masses or 'blobs'. We found that the model detects wood with a mean average precision of 67 percent when using a 418 pixels input image resolution. Also, improvements of up to 23 percent could be achieved in some instances and increasing the input resolution raised the weighted mean average precision to 74 percent. We show that the detection performance on a specific dataset is not solely determined by the complexity of the network or the training data. Therefore, the findings of this paper can be used when designing a custom wood detection network. With the growing availability of flood-related videos featuring wood uploaded to the internet, this methodology facilitates the quantification of wood transport across a wide variety of data sources. [ABSTRACT FROM AUTHOR]

Diseases of tomato leaves can seriously damage crop yield and financial rewards. The timely and accurate detection of tomato diseases is a major challenge in agriculture. Hence, the early and accurate diagnosis of tomato diseases is crucial. The emergence of deep learning has dramatically helped in plant disease detection. However, the accuracy of deep learning models largely depends on the quantity and quality of training data. To solve the inter-class imbalance problem and improve the generalization ability of the classification model, this paper proposes a cycle-consistent generative-adversarial-network-based Transformer model to generate diseased tomato leaf images for data augmentation. In addition, this paper uses a Transformer model and densely connected CNN architecture to extract multilevel local features. The Transformer module is utilized to capture global dependencies and contextual information accurately to expand the sensory field of the model. Experiments show that the proposed model achieved 99.45% accuracy on the PlantVillage dataset. The 2018 Artificial Intelligence Challenger dataset and the private dataset attained accuracies of 98.30% and 95.4%, and the proposed classification model achieved a higher accuracy and smaller model size compared to previous deep learning models. The classification model is generalizable and robust and can provide a stable theoretical framework for crop disease prevention and control. [ABSTRACT FROM AUTHOR]

Object detection (OD) networks trained with CAD-based synthetic datasets still face significant challenges in detecting real mechanical parts in heavily cluttered industry scenes. This paper proposes a novel two-stage filtering method to improve detection performance. In the first stage, in order to increase the precision and recall of OD, a novel method for optimizing the position of pasted parts is discussed to increase the variety of synthetic datasets, and a novel DoG-MS module is designed and seamlessly integrated into the original networks. In the second stage, high-performance image classification networks, subsequently used as a filter, are designed based on yolov5s and transfer learning. Then an effective filtering strategy is designed to improve the precision of object detection further. Extensive experimental results show that compared to the original OD networks, the two-stage filtering method can improve the mean precision, mean recall, and mAP by 7.5%, 3.5%, and 3.9%, respectively. The proposed method has the potential to expand the application range of CAD-based synthetic datasets in the field of industrial manufacturing. [ABSTRACT FROM AUTHOR]

Sediment grains are progressively rounded during their transport down a river. For more than a century, Earth scientists have used the roundness of pebbles within modern sediment, and of clasts within conglomerates, as a key metric to constrain the sediment's transport history and source area(s). However, the current practices of assessment of pebble roundness are mainly qualitative and based on time-consuming manual measurement methods. This qualitative judgement provides the transport history only in a broad sense, such as classifying distance as "near" or "far". In this study, we propose a new model that quantifies the relationship between roundness and the transport distance. We demonstrate that this model can be applied to the clasts of multiple lithologies including modern sediment, as well as conglomerates, deposited by ancient river systems. We present field data from two Himalayan catchments in Nepal. We use the normalized isoperimetric ratio (IRn), which relates a pebble's area (A) to its perimeter (P), to quantify roundness. The maximum analytical value for IRn is 1, and IRn is expected to increase with transport distance. We propose a non-linear roundness model based on our field data, whereby the difference between a grain's IRn and the maximum value of 1 decays exponentially with transport distance, mirroring Sternberg's model of mass loss or size reduction by abrasion. This roundness model predicts an asymptotic behaviour for IRn , and the distance over which IRn approaches the asymptote is controlled by a rounding coefficient. Our field data suggest that the roundness coefficient for granite pebbles is 9 times that of quartzite pebbles. Using this model, we reconstruct the transport history of a Pliocene paleo-river deposit preserved at the base of the Kathmandu intermontane basin. These results, along with other sedimentary evidence, imply that the paleo-river was much longer than the length of the Kathmandu Basin and that it must have lost its headwaters through drainage capture. We further explore the extreme rounding of clasts from Miocene conglomerate of the Siwalik zone and find evidence of sediment recycling. [ABSTRACT FROM AUTHOR]

The use of deep learning techniques to identify grape leaf diseases relies on large, high-quality datasets. However, a large number of images occupy more computing resources and are prone to pattern collapse during training. In this paper, a depth-separable multifeature generative adversarial network (DMFGAN) was proposed to enhance grape leaf disease data. First, a multifeature extraction block (MFEB) based on the four-channel feature fusion strategy is designed to improve the quality of the generated image and avoid the problem of poor feature learning ability of the adversarial generation network caused by the single-channel feature extraction method. Second, a depth-based D-discriminator is designed to improve the discriminator capability and reduce the number of model parameters. Third, SeLU activation function was substituted for DCGAN activation function to overcome the problem that DCGAN activation function was not enough to fit grape leaf disease image data. Finally, an MFLoss function with a gradient penalty term is proposed to reduce the mode collapse during the training of generative adversarial networks. By comparing the visual indicators and evaluation indicators of the images generated by different models, and using the recognition network to verify the enhanced grape disease data, the results show that the method is effective in enhancing grape leaf disease data. Under the same experimental conditions, DMFGAN generates higher quality and more diverse images with fewer parameters than other generative adversarial networks. The mode breakdown times of generative adversarial networks in training process are reduced, which is more effective in practical application., (© 2024 Society for Experimental Biology and John Wiley & Sons Ltd.)

Object detection for industrial applications faces challenges that are yet to solve by state-of-the-art deep learning models. They usually lack training data, and the common solution of using a synthetic dataset introduces a domain gap when the model is provided real images. Besides, few architectures fit in the small memory of a mobile device and run in real-time with limited computation capabilities. The models fulfilling these requirements generally have low learning capacity, and the domain gap reduces further the performance. In this work, we propose multiple strategies to reduce the domain gap when using RGB-D images, and to increase the overall performance of a Convolutional Neural Network (CNN) for object detection with a reasonable increase of the model size. First, we propose a new architecture based on the Single Shot Detector (SSD) architecture, and we compare different fusion methods to increase the performance with few or no additional parameters. We applied the proposed method to three synthetic datasets with different visual characteristics, and we show that classical image processing reduces significantly the domain gap for depth maps. Our experiments have shown an improvement when fusing RGB and depth images for two benchmark datasets, even when the depth maps contain few discriminative information. Our RGB-D SSD Lite model performs on par or better than a ResNet-FPN RetinaNet model on the LINEMOD and T-LESS datasets, while requiring 20 times less computation. Finally, we provide some insights on training a robust model for improved performance when one of the modalities is missing. [ABSTRACT FROM AUTHOR]

Based on the sclereids in the bark of oak species, a convolutional neural network (CNN) was employed to validate species classification performance and its influencing factors. Three optimizers including stochastic gradient descent (SGD), adaptive moment estimation (Adam), root mean square propagation (RMSProp), and dataset augmentation were adopted. The accuracy and loss stabilized at approximately 15 to 20 and 70 to 80 epochs for the augmented and non-augmented condition, respectively. In the last five epochs, the RMSProp-augmented condition achieved the highest accuracy of 89.8%, whereas the Adam-augmented condition achieved the lowest accuracy of 73.8%. Regarding the loss, SGD-non-augmented condition was the lowest at 0.498, whereas Adamaugmented condition was the highest at 2.740. The highest accuracy was influenced by RMSProp at 0.194. Dataset augmentation had a significant influence on accuracy at 0.456. Homogeneous subsets among the validation conditions indicated that the accuracy and loss were classified into the same subset using an augmented dataset during the training, regardless of the optimizer. Only Adam and RMSProp with nonaugmented datasets were categorized into the same subset during the test. Hence, species classification using CNN and sclereid characteristics in the bark was feasible, and RMSProp with augmented datasets showed optimal performance for species classification. [ABSTRACT FROM AUTHOR]

As remote sensing transforms forest and urban tree management, automating tree species classification is now a major challenge to harness these advances for forestry and urban management. This study investigated the use of structural bark features from terrestrial laser scanner point cloud data for tree species identification. It presents a novel mathematical approach for describing bark characteristics, which have traditionally been used by experts for the visual identification of tree species. These features were used to train four machine learning algorithms (decision trees, random forests, XGBoost, and support vector machines). These methods achieved high classification accuracies between 83% (decision tree) and 96% (XGBoost) with a data set of 85 trees of four species collected near Krakow, Poland. The results suggest that bark features from point cloud data could significantly aid species identification, potentially reducing the amount of training data required by leveraging centuries of botanical knowledge. This computationally efficient approach might allow for real-time species classification. [ABSTRACT FROM AUTHOR]

Problems: Plant Disease diagnosis based on deep learning mechanisms has been extensively studied and applied. However, the complex and dynamic agricultural growth environment results in significant variations in the distribution of state samples, and the lack of sufficient real disease databases weakens the information carried by the samples, posing challenges for accurately training models. Aim: This paper aims to test the feasibility and effectiveness of Denoising Diffusion Probabilistic Models (DDPM), Swin Transformer model, and Transfer Learning in diagnosing citrus diseases with a small sample. Methods: Two training methods are proposed: The Method 1 employs the DDPM to generate synthetic images for data augmentation. The Swin Transformer model is then used for pre-training on the synthetic dataset produced by DDPM, followed by fine-tuning on the original citrus leaf images for disease classification through transfer learning. The Method 2 utilizes the pre-trained Swin Transformer model on the ImageNet dataset and fine-tunes it on the augmented dataset composed of the original and DDPM synthetic images. Results and conclusion: The test results indicate that Method 1 achieved a validation accuracy of 96.3%, while Method 2 achieved a validation accuracy of 99.8%. Both methods effectively addressed the issue of model overfitting when dealing with a small dataset. Additionally, when compared with VGG16, EfficientNet, ShuffleNet, MobileNetV2, and DenseNet121 in citrus disease classification, the experimental results demonstrate the superiority of the proposed methods over existing approaches to a certain extent. [ABSTRACT FROM AUTHOR]

Copyright of Environnement, Risques & Santé is the property of John Libbey Eurotext Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Apple leaf diseases typified by small disease spots are generally difficult to detect in images. This study proposes a deep learning model called the feature pyramid networks (FPNs) –inception squeeze-and-excitation ResNet (ISResNet)–Faster RCNN (region with convolutional neural network) model to improve the accuracy of detecting apple leaf diseases. Apple leaf diseases were identified, evaluated, and validated by using the FPN–ISResNet–Faster RCNN. The results were compared with those obtained by the single-shot multibox detector (SSD), Faster RCNN, and ISResNet–Faster RCNN. The detection accuracies obtained by using different feature extraction networks, positions and numbers of SE, inception modules, scales of FPN structures, and scales of anchor frames were also compared. The results showed that the values of average precision (AP), and APs with the thresholds of the intersection over union of 0.5 and 0.75 (AP50 and AP75), obtained from the FPN–ISResNet–Faster RCNN were 62.71%, 93.68%, and 70.94%, respectively, which are higher than those of the SSD, VGG–Faster RCNN, GoogleNet–Faster RCNN, ResNet50–Faster RCNN, ResNeXt–Faster RCNN, and ISResNet–Faster RCNN. FPN–ISResNet–Faster RCNN was shown to be able to detect diseases in apple leaves with high accuracy and generalizability. [ABSTRACT FROM AUTHOR]

Sediment grains are progressively rounded during their transport down a river. For more than a century, Earth scientists have used the roundness of pebbles within modern sediment, and of clasts within conglomerates, as a key metric to constrain the sediment's transport history and source area(s). However, the current practices of assessment of pebble roundness are mainly qualitative and based on time consuming manual measurement methods. This qualitative judgement provides the transport history only in a broad sense, such as classifying distance as 'near' or 'far'. In this study, we propose a new model that quantifies the relationship between roundness and the transport distance. We demonstrate that this model can be applied to the clasts of multiple lithologies including modern sediment as well as conglomerates deposited by ancient river systems. We present field data from two Himalayan catchments in Nepal. We use the Normalized Isoperimetric Ratio (IRn) which relates a pebble's area (A) to its perimeter (P), to quantify roundness. The maximum analytical value for IRn is 1, and IRn is expected to increase with transport distance. We propose a non-linear roundness model based on our field data, whereby the difference between a grain's IRn and the maximum value of 1 decays exponentially with transport distance, mirroring Sternberg's model of mass loss or size reduction by abrasion. This roundness model predicts an asymptotic behaviour for IRn , and the distance over which IRn approaches the asymptote is controlled by a rounding coefficient. Our field data suggest that the roundness coefficient for granite pebbles is eight times that of quartzite pebbles. Using this model, we reconstruct the transport history of a Pliocene paleo-river deposit preserved at the base of the Kathmandu intermontane Basin. These results, along with other sedimentary evidence, imply that the paleo-river was much longer than the length of the Kathmandu Basin, and that it must have lost its headwaters through drainage capture. We further explore the extreme rounding of clasts from Miocene conglomerate of the Siwaliks Zone and find evidence of sediment recycling. [ABSTRACT FROM AUTHOR]

Artificial perception for robots operating in outdoor natural environments, including forest scenarios, has been the object of a substantial amount of research for decades. Regardless, this has proven to be one of the most difficult research areas in robotics and has yet to be robustly solved. This happens namely due to difficulties in dealing with environmental conditions (trees and relief, weather conditions, dust, smoke, etc.), the visual homogeneity of natural landscapes as opposed to the diversity of natural obstacles to be avoided, and the effect of vibrations or external forces such as wind, among other technical challenges. Consequently, we propose a new survey, describing the current state of the art in artificial perception and sensing for robots in precision forestry. Our goal is to provide a detailed literature review of the past few decades of active research in this field. With this review, we attempted to provide valuable insights into the current scientific outlook and identify necessary advancements in the area. We have found that the introduction of robotics in precision forestry imposes very significant scientific and technological problems in artificial sensing and perception, making this a particularly challenging field with an impact on economics, society, technology, and standards. Based on this analysis, we put forward a roadmap to address the outstanding challenges in its respective scientific and technological landscape, namely the lack of training data for perception models, open software frameworks, robust solutions for multi-robot teams, end-user involvement, use case scenarios, computational resource planning, management solutions to satisfy real-time operation constraints, and systematic field testing. We argue that following this roadmap will allow for robotics in precision forestry to fulfil its considerable potential. [ABSTRACT FROM AUTHOR]

Machine learning is a crucial tool for both academic and real-world applications. Classification problems are often used as the preferred showcase in this space, which has led to a wide variety of datasets being collected and utilized for a myriad of applications. Unfortunately, there is very little standardization in how these datasets are collected, processed, and disseminated. As new learning paradigms like lifelong or meta-learning become more popular, the demand for merging tasks for at-scale evaluation of algorithms has also increased. This paper provides a methodology for processing and cleaning datasets that can be applied to existing or new classification tasks as well as implements these practices in a collection of diverse classification tasks called USC-DCT. Constructed using 107 classification tasks collected from the internet, this collection provides a transparent and standardized pipeline that can be useful for many different applications and frameworks. While there are currently 107 tasks, USC-DCT is designed to enable future growth. Additional discussion provides explanations of applications in machine learning paradigms such as transfer, lifelong, or meta-learning, how revisions to the collection will be handled, and further tips for curating and using classification tasks at this scale. Dataset:  https://github.com/iLab-USC/USC-DCT Dataset License: CC-BY-NC [ABSTRACT FROM AUTHOR]

This paper presents the object detection algorithms GRASS GIS applied for Landsat 8-9 OLI/TIRS data. The study area includes the Sudd wetlands located in South Sudan. This study describes a programming method for the automated processing of satellite images for environmental analytics, applying the scripting algorithms of GRASS GIS. This study documents how the land cover changed and developed over time in South Sudan with varying climate and environmental settings, indicating the variations in landscape patterns. A set of modules was used to process satellite images by scripting language. It streamlines the geospatial processing tasks. The functionality of the modules of GRASS GIS to image processing is called within scripts as subprocesses which automate operations. The cutting-edge tools of GRASS GIS present a cost-effective solution to remote sensing data modelling and analysis. This is based on the discrimination of the spectral reflectance of pixels on the raster scenes. Scripting algorithms of remote sensing data processing based on the GRASS GIS syntax are run from the terminal, enabling to pass commands to the module. This ensures the automation and high speed of image processing. The algorithm challenge is that landscape patterns differ substantially, and there are nonlinear dynamics in land cover types due to environmental factors and climate effects. Time series analysis of several multispectral images demonstrated changes in land cover types over the study area of the Sudd, South Sudan affected by environmental degradation of landscapes. The map is generated for each Landsat image from 2015 to 2023 using 481 maximum-likelihood discriminant analysis approaches of classification. The methodology includes image segmentation by 'i.segment' module, image clustering and classification by 'i.cluster' and 'i.maxlike' modules, accuracy assessment by 'r.kappa' module, and computing NDVI and cartographic mapping implemented using GRASS GIS. The benefits of object detection techniques for image analysis are demonstrated with the reported effects of various threshold levels of segmentation. The segmentation was performed 371 times with 90% of the threshold and minsize = 5; the process was converged in 37 to 41 iterations. The following segments are defined for images: 4515 for 2015, 4813 for 2016, 4114 for 2017, 5090 for 2018, 6021 for 2019, 3187 for 2020, 2445 for 2022, and 5181 for 2023. The percent convergence is 98% for the processed images. Detecting variations in land cover patterns is possible using spaceborne datasets and advanced applications of scripting algorithms. The implications of cartographic approach for environmental landscape analysis are discussed. The algorithm for image processing is based on a set of GRASS GIS wrapper functions for automated image classification. [ABSTRACT FROM AUTHOR]

Context: Striking land-use changes after WW II characterize the past century in the European Alps with impact on ecosystems and biodiversity. Documenting land-use changes is often difficult due to limited information from the past. Mapping landscape history with aerial photography can foster the understanding of human-induced changes in vulnerable ecosystems, such as the remnants of dry grasslands in the Central Alps. Objectives: We aimed to assess changes in grassland vegetation and their current extent in Val Venosta (European Alps, Italy) in relation to overall landscape settings, anthropogenic drivers of change and the effectiveness of the protected areas. Methods: We performed a land-cover classification based on a mixed machine learning approach including several auxiliary classifiers in a random forest model to characterise the extent and state of (dry) grasslands. We calculated landscape metrics between 1945 and 2015 to assess shape-related changes, especially regarding their landscape embedding and the protection status of sites. Results: Three main processes related to a changing extent in grassland habitat prevail: (i) agricultural intensification, (ii) settlement expansion at the valley bottom and (iii) forest expansion (afforestation and encroachment due to decreasing pasture activities) on the valley slopes. The remaining grassland habitat is increasingly isolated and fragmented, leaving only few core areas of dry grassland, which tended to be better conserved within protected areas. Conclusion: The changes in extent of dry grasslands revealed marked changes. Transformations are assumed to be predominantly caused by human impact and successional changes. Our results confirm the importance of protected area networks. The pronounced landscape changes underline the urgent need for future research with explicit focus on the changes at community level and the underlying causes. Identifying all relevant drivers of change should be a key element in targeted conservation efforts. [ABSTRACT FROM AUTHOR]

Correspondences between geometric domains (mappings) are ubiquitous in computer graphics and engineering, both for a variety of downstream applications and as core building blocks for higher level algorithms. In particular, mapping a shape to a convex or star‐shaped domain with simple geometry is a fundamental module in existing pipelines for mesh generation, solid texturing, generation of shape correspondences, advanced manufacturing etc. For the case of surfaces, computing such a mapping with guarantees of injectivity is a solved problem. Conversely, robust algorithms for the generation of injective volume mappings to simple polytopes are yet to be found, making this a fundamental open problem in volume mesh processing. VOLMAP is a large scale benchmark aimed to support ongoing research in volume mapping algorithms. The dataset contains 4.7K tetrahedral meshes, whose boundary vertices are mapped to a variety of simple domains, either convex or star‐shaped. This data constitutes the input for candidate algorithms, which are then required to position interior vertices in the domain to obtain a volume map. Overall, this yields more than 22K alternative test cases. VOLMAP also comprises tools to process this data, analyze the resulting maps, and extend the dataset with new meshes, boundary maps and base domains. This article provides a brief overview of the field, discussing its importance and the lack of effective techniques. We then introduce both the dataset and its major features. An example of comparative analysis between two existing methods is also present. [ABSTRACT FROM AUTHOR]

Super HAD CCD and ISOCELL GW1 imaging sensors are used for capturing images in high-resolution cameras nowadays. These high-resolution camera sensors were used in this work to acquire black gram plant leaf diseased images in natural cultivation fields. Segmenting plant leaf regions from the black gram cultivation field images is a preliminary step for disease identification and classification. It is also helpful for the farmers to assess the plants' health and identify the diseases in their early stages. Even though plant leaf region segmentation has been effectively handled in many contributions, no universally applicable solution exists to solve all issues. Therefore, an approach for extracting leaf region from black gram plant leaf images is presented in this article. The novelty of the proposed method is that MobileNetV2 has been utilized as a backbone network for DeepLabv3+ layers to segment plant leaf regions. The DeepLabv3+ with MobileNetV2 segmentation model exhibited superior performance compared to the other models (SegNet, U-Net, DeepLabv3+ with ResNet18, ResNet50, Xception, and InceptionResNetV2) in terms of accuracy of 99.71%, Dice of 98.72%, and Jaccard/IoU of 97.47% when data augmentation was applied. The algorithms were developed and trained using MATLAB software. Each of the experimental trials reported in this article surpasses the prior findings. [ABSTRACT FROM AUTHOR]