RafanoSet: Dataset of raw, manually, and automatically annotated Raphanus Raphanistrum weed images for object detection and segmentation.

The rationale for this data article is to provide resources which could facilitate the studies focussed over weed detection and segmentation in precision farming using computer vision. We have curated Multispectral (MS) images over crop fields of Triticum Aestivum containing heterogenous mix of Raphanus raphanistrum in both uniform and random crop spacing. This dataset is designed to facilitate weed detection and segmentation based on manual and automatically annotated Raphanus raphanistrum, commonly known as wild radish. The dataset is publicly available through the Zenodo data library and provides annotated pixel-level information that is crucial for registration and segmentation purposes. The dataset consists of 85 original MS images captured over 17 scenes covering various spectra including Blue, Green, Red, NIR (Near-Infrared), and RedEdge. Each image has a dimension of 1280 × 960 pixels and serves as the basis for the specific weed detection and segmentation. Manual annotations were performed using Visual Geometry Group Image Annotator (VIA) and the results were saved in Common Objects in Context (COCO) segmentation format. To facilitate this resource-intensive task of annotation, a Grounding DINO + Segment Anything Model (SAM) was trained with this manually annotated data to obtain automated Visual Object Classes Extended Markup Language (PASCAL VOC) annotations for 80 MS images. The dataset emphasizes quality control, validating both the 'manual" and 'automated" repositories by extracting and evaluating binary masks. The codes used for these processes are accessible to ensure transparency and reproducibility. This dataset is the first-of-its-kind public resource providing manual and automatically annotated weed information over close-ranged MS images in heterogenous agriculture environment. Researchers and practitioners in the fields of precision agriculture and computer vision can use this dataset to improve MS image registration and segmentation at close range photogrammetry with a focus on wild radish. The dataset not only helps with intra-subject registration to improve segmentation accuracy, but also provides valuable spectral information for training and refining machine learning models.

GobhiSet: Dataset of raw, manually, and automatically annotated RGB images across phenology of Brassica oleracea var. Botrytis.

This research introduces an extensive dataset of unprocessed aerial RGB images and orthomosaics of Brassica oleracea crops, captured via a DJI Phantom 4. The dataset, publicly accessible, comprises 244 raw RGB images, acquired over six distinct dates in October and November of 2020 as well as 6 orthomosaics from an experimental farm located in Portici, Italy. The images, uniformly distributed across crop spaces, have undergone both manual and automatic annotations, to facilitate the detection, segmentation, and growth modelling of crops. Manual annotations were performed using bounding boxes via the Visual Geometry Group Image Annotator (VIA) and exported in the Common Objects in Context (COCO) segmentation format. The automated annotations were generated using a framework of Grounding DINO + Segment Anything Model (SAM) facilitated by YOLOv8x-seg pretrained weights obtained after training manually annotated images dated 8 October, 21 October, and 29 October 2020. The automated annotations were archived in Pascal Visual Object Classes (PASCAL VOC) format. Seven classes, designated as Row 1 through Row 7, have been identified for crop labelling. Additional attributes such as individual crop ID and the repetitiveness of individual crop specimens are delineated in the Comma Separated Values (CSV) version of the manual annotation. This dataset not only furnishes annotation information but also assists in the refinement of various machine learning models, thereby contributing significantly to the field of smart agriculture. The transparency and reproducibility of the processes are ensured by making the utilized codes accessible. This research marks a significant stride in leveraging technology for vision-based crop growth monitoring.

Comprehensive Evaluation of Multispectral Image Registration Strategies in Heterogenous Agriculture Environment.

This article is focused on the comprehensive evaluation of alleyways to scale-invariant feature transform (SIFT) and random sample consensus (RANSAC) based multispectral (MS) image registration. In this paper, the idea is to extensively evaluate three such SIFT- and RANSAC-based registration approaches over a heterogenous mix containing Triticum aestivum crop and Raphanus raphanistrum weed. The first method is based on the application of a homography matrix, derived during the registration of MS images on spatial coordinates of individual annotations to achieve spatial realignment. The second method is based on the registration of binary masks derived from the ground truth of individual spectral channels. The third method is based on the registration of only the masked pixels of interest across the respective spectral channels. It was found that the MS image registration technique based on the registration of binary masks derived from the manually segmented images exhibited the highest accuracy, followed by the technique involving registration of masked pixels, and lastly, registration based on the spatial realignment of annotations. Among automatically segmented images, the technique based on the registration of automatically predicted mask instances exhibited higher accuracy than the technique based on the registration of masked pixels. In the ground truth images, the annotations performed through the near-infrared channel were found to have a higher accuracy, followed by green, blue, and red spectral channels. Among the automatically segmented images, the accuracy of the blue channel was observed to exhibit a higher accuracy, followed by the green, near-infrared, and red channels. At the individual instance level, the registration based on binary masks depicted the highest accuracy in the green channel, followed by the method based on the registration of masked pixels in the red channel, and lastly, the method based on the spatial realignment of annotations in the green channel. The instance detection of wild radish with YOLOv8l-seg was observed at a mAP@0.5 of 92.11% and a segmentation accuracy of 98% towards segmenting its binary mask instances.

Combining Integrated Informative System and Historical Digital Twin for Maintenance and Preservation of Artistic Assets.

The protection of artistic and cultural heritage is a major challenge due to its peculiarities and its exposure to significant natural hazards. Several methodologies exist to assess the condition of artistic heritage and to protect it from exceptional actions. Moreover, novel digital technologies offer many solutions able to deliver a digital replica of artifacts of interest, so that a reduction in the uncertainties in the analysis models can be achieved. A rational approach to the preservation and protection of artistic heritage is based on traditional approaches supported and integrated by novel technologies, so that qualitative and quantitative indicators of the current condition of artistic heritage can be defined and validated in an interdisciplinary framework. The present paper reports the results of an approach to the maintenance and preservation of art objects housed in a museum complex based on a comprehensive digital path towards a Historical Digital Twin (HDT). A workflow aimed at estimating the stress regime and the dynamic properties of two sculptures, based on the detailed three-dimensional model resulting from a laser scanner survey, is illustrated and discussed. The results highlight the great advantages resulting from the integration of traditional and novel procedures in the field of conservation of artistic assets.

Towards Digital Twin Implementation for Assessing Production Line Performance and Balancing.

The optimization of production processes has always been one of the cornerstones for manufacturing companies, aimed to increase their productivity, minimizing the related costs. In the Industry 4.0 era, some innovative technologies, perceived as far away until a few years ago, have become reachable by everyone. The massive introduction of these technologies directly in the factories allows interconnecting the resources (machines and humans) and the entire production chain to be kept under control, thanks to the collection and the analyses of real production data, supporting the decision making process. This article aims to propose a methodological framework that, thanks to the use of Industrial Internet of Things-IoT devices, in particular the wearable sensors, and simulation tools, supports the analyses of production line performance parameters, by considering both experimental and numerical data, allowing a continuous monitoring of the line balancing and performance at varying of the production demand. A case study, regarding a manual task of a real manufacturing production line, is presented to demonstrate the applicability and the effectiveness of the proposed procedure.

Improving comfort of shoe sole through experiments based on CAD-FEM modeling.

It was reported that next to style, comfort is the second key aspect in purchasing footwear. One of the most important components of footwear is the shoe sole, whose design is based on many factors such as foot shape/size, perceived comfort and materials. The present paper focuses on the parametric analysis of a shoe sole to improve the perceived comfort. The sensitivity of geometric and material design factors on comfort degree was investigated by combining real experimental tests and CAD-FEM simulations. The correlation between perceived comfort and physical responses, such as plantar pressures, was estimated by conducting real tests. Four different conditions were analyzed: subjects wearing three commercially available shoes and in a barefoot condition. For each condition, subjects expressed their perceived comfort score. By adopting plantar sensors, the plantar pressures were also monitored. Once given such a correlation, a parametric FEM model of the footwear was developed. In order to better simulate contact at the plantar surface, a detailed FEM model of the foot was also generated from CT scan images. Lastly, a fractional factorial design array was applied to study the sensitivity of different sets of design factors on comfort degree. The findings of this research showed that the sole thickness and its material highly influence perceived comfort. In particular, softer materials and thicker soles contribute to increasing the degree of comfort.

A comparison between customized clear and removable orthodontic appliances manufactured using RP and CNC techniques.

OBJECTIVES: Aim of the research is to compare the orthodontic appliances fabricated by using rapid prototyping (RP) systems, in particular 3D printers, with those manufactured by using computer numerical control (CNC) milling machines. 3D printing is today a well-accepted technology to fabricate orthodontic aligners by using the thermoforming process, instead the potential of CNC systems in dentistry have not yet been sufficiently explored. MATERIALS AND METHODS: One patient, with mal-positioned maxillary central and lateral incisors, was initially selected. In the computer aided virtual planning was defined that, for the treatment, the patient needed to wear a series of 7 removable orthodontic appliances (ROA) over a duration of 21 weeks, with one appliance for every 3 weeks. A non-contact reverse engineering (RE) structured-light 3D scanner was used to create the 3D STL model of the impression of the patient's mouth. Numerical FEM simulations were performed varying the position of applied forces (discrete and continuous forces) on the same model, simulating, in this way, 3 models with slice thickness of 0.2 mm, 0.1 mm (RP staircase effect) and without slicing (ideal case). To define the areas of application of forces, two configuration "i" and "i-1" of the treatment were overlapped. 6 patients to which for three steps (3rd, 4th and 5th step) were made to wear aligners fabricated starting from physical models by 3D printing (3DP-ROA) and afterwards, for the next steps (6th, 7th and 8th step), aligners fabricated starting from physical models by CNC milling machine (CNC-ROA), were selected. RESULTS: For the 6 patients wearing the CNC-ROA, it was observed a best fitting of the aligner to the teeth and a more rapid teeth movement than the 3DP-ROA (2 weeks compared to 3 weeks for every appliance). FEM simulations showed a more uniform stress distribution for CNC-ROA than 3DP-ROA. CONCLUSIONS: In this research, 6 different case studies and CAD-FEM simulations showed that, to fabricate an efficient clear and removable orthodontic aligner, it is necessary to consider a compromise of several factors. A lower staircase effect (lower layer thickness) and a higher physical prototype accuracy allow a better control of tooth movement.

Stereolithography in oral implantology: a comparison of surgical guides.

This article presents the use of stereolithography in oral implantology. Stereolithography is a new technology that can produce physical models by selectively solidifying an ultraviolet-sensitive liquid resin using a laser beam, reproducing the true maxillary and mandibular anatomic dimensions. With these models, it is possible to fabricate surgical guides that can place the implants in vivo in the same places and same directions as those in the planned computer simulation. A 70-year-old woman, in good health, with severe mandibular bone atrophy was rehabilitated with an over-denture supported by 2 Branemark implants. Two different surgical planning methods were considered: 1) the construction of a surgical guide evaluating clinical aspects, and 2) the surgical guide produced by stereolithographic study. The accuracy of surgical planning can reduce the problems related to bone density and dimensions. Furthermore, the stereolithographic study assured the clinicians of a superior location of fixtures in bone. Surgical planning based on stereolithographic technique is a safe procedure and has many advantages. This technologic advance has biologic and therapeutic benefits because it simplifies anatomic surgical management for improved implant placement.