278 research outputs found
Vision-Based Production of Personalized Video
No full textIn this paper we present a novel vision-based system for the automated production of personalised video souvenirs for visitors in leisure and cultural heritage venues. Visitors are visually identified and tracked through a camera network. The system produces a personalized DVD souvenir at the end of a visitor’s stay allowing visitors to relive their experiences. We analyze how we identify visitors by fusing facial and body features, how we track visitors, how the tracker recovers from failures due to occlusions, as well as how we annotate and compile the final product. Our experiments demonstrate the feasibility of the proposed approach
Using Earth Observation Application to Air Quality in Addition to in-situ monitoring: HARMONIA IRAP platform
No full textThe effect of air quality (AQ) on public health after the COVID-19 pandemic attracted more attention although this undeniable link was studied before. Such diseases caused or accelerated by the air pollution levels has a long list including respiratory, cardiovascular, and lung disease. There are different associations between air pollution and the diseases i.e., long-term, short-term exposure and finally higher levels of air pollution. To improve a healthy environment in urban areas, increasing AQ is a must and in-situ monitoring is one method to track it. To combine in-situ monitored data and earth observation (EO) data could provide an efficient way to collect data in different temporal resolution, analyze, detect any existing anomalies, eventually provide a model for possible scenarios through climate change. This paper will discuss the benefits and challenges lie under the combination of in-situ and EO data in this framework. It will present the suggested integrated resilience assessment platform (IRAP) that is under development in the HARMONIA project (in respond to the topic LC-CLA-19-2020 and its added value on this field. The IRAP platform will eventually utilize the GEOSS datasets, along with other data collections, and adopt proper Deep Learning techniques in an effort to build robust, comprehensive data cube objects, which are considered to be the state-of-the-art solution to store and organize EO data. Information extracted from the datacubes will be visualized in the integrated graphical user interface of the platform in order to inform municipalities and citizens for potential climate change related risks and vulnerabilities
Minimally invasive congenital cardiac surgery: A large volume european experience
No full textBackground: In an effort to reduce postoperative trauma and achieve more cosmetic results, minimally invasive approaches to correct congenital heart anomalies have been recently proposed and increasingly adopted. Here we describe our experience for the past 23 years. Methods: Patients who underwent a surgical procedure between February 1996 and March 2019 with a minimally invasive approach for the correction of congenital heart disease in our center were included in this study. A statistical analysis was carried out to compare the results of the different minimally invasive techniques. A meta-analysis was conducted to compare our results in patients undergoing atrial septal defect repair with those from other groups. Results: There were 1002 patients included. A midline lower mini-sternotomy was performed in 45% of patients (n = 455), a right anterior mini-thoracotomy in 36% (n = 356) and a right lateral mini-thoracotomy in 19% (n = 191). The procedures were atrial septal defect repair (n = 575, 57%), ventricular septal defect repair (n = 218, 22%), and correction of atrioventricular defect (n = 82, 8%) or partial anomalous pulmonary venous return (n = 70, 7%). Post-cardiotomy syndrome was the most frequent complication (n = 40, 4%). No difference was observed between the approaches in terms of complications and peri-operative outcomes, and when these were compared with the results of other centers. Conclusions: Patients undergoing surgical repair of congenital heart disease through a minimally invasive approach have excellent outcomes, regardless of the approach used
High Dynamic Range in Cultural Heritage Applications
No full textHigh dynamic range (HDR) technology enables the capture, storage, transmission and display of real-world lighting at a high precision as opposed to traditional low dynamic range (LDR) imaging. One of HDR’s main features is its ability to reproduce very bright and very dark areas simultaneously. Dynamic range describes the span between these extrema in the brightness scale. HDR research investigates the generation, capturing, processing, transmission, storage and reproduction of HDR content. Cultural heritage represents our legacy that must be passed on to future generations. As it is increasingly threatened with deterioration, destruction and disappearance, its documentation, conservation and presentation is of high importance. Given the real-world dynamic range and the limitations of conventional capture and display technology, HDR imaging represents an invaluable tool for accurate documentation, virtual reconstruction and visualisation of cultural heritage. HDR is used by academics, museums, and media to visualise the appearance of sites in various periods in time. Physically-based 3D virtual reconstructions are used for studying existing or ruined cultural heritage environments. This in turn enables archaeologists to interpret the past and deduce new historical knowledge. In this chapter we present the HDR pipeline, along with its use for cultural heritage preservation, recreation and presentation
Goat-CNN: A Lightweight Convolutional Neural Network for Pose-Independent Body Condition Score Estimation in Goats
No full text<p>Here we introduce the dataset utilized in our published paper entitled "<a href="https://www.sciencedirect.com/science/article/pii/S2666154324002114">Goat-CNN: A Lightweight Convolutional Neural Network for Pose-Independent Body Condition Score Estimation in Goats</a>".</p>
<p>Contained within the "bcs" folder are all the videos collected for this study. Each video file is named with a format denoting its respective details. The first number signifies the sequence of collection, the second denotes the ear tag, and the final figure represents the body condition score (BCS) value.</p>
<p>For example: "1_158734_2.50" indicates the first sampling of an animal with the ear tag "158734" and a BCS value of "2.50".</p>
<p>Additionally, we provide two Python scripts in this repository. The first script, "Video2Frame.py", facilitates the splitting of videos into individual frames. The second script, "Frames2npy.py", converts these frames into two numpy-friendly files with the extension ".npy". These files contain both the images ("X_train_bcs300.npy") and their corresponding labels ("Y_train_bcs300.npy").</p>
<p>Furthermore, for the convenience of swift experimentation, we have included the desired .npy files within the repository.</p>
<p>To load these files into your Python environment, you can use the following code snippet:</p>
<div>
<div>th4figs = '/content/drive/MyDrive/compag_2023/'</div>
<br>
<div>path4images = "/content/drive/MyDrive/CodeRefarm/datasets/BCS/X_train_bcs300.npy"</div>
<div>Xtrain = np.load(path4images)</div>
<br>
<div>path4labels = "/content/drive/MyDrive/CodeRefarm/datasets/BCS/Y_train_bcs300.npy"</div>
<div>Ytrain = np.load(path4labels).astype(float)</div>
<br>
<div>print("X train : ", Xtrain.shape)</div>
<div>print("Y train : ", Ytrain.shape)</div>
<div>
<div>
<div>
<div>
<div>
<div>
<div> </div>
</div>
<div> </div>
</div>
</div>
</div>
</div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<div>
<pre>X train : (5332, 300, 300, 3)
Y train : (5332,)<br>
</pre>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div><p>If you want to cite this work you can use the following text:</p>
<p>@article{TEMENOS2024101174,<br>title = {Goat-CNN: A lightweight convolutional neural network for pose-independent body condition score estimation in goats},<br>journal = {Journal of Agriculture and Food Research},<br>volume = {16},<br>pages = {101174},<br>year = {2024},<br>issn = {2666-1543},<br>doi = {https://doi.org/10.1016/j.jafr.2024.101174},<br>url = {https://www.sciencedirect.com/science/article/pii/S2666154324002114},<br>author = {Anastasios Temenos and Athanasios Voulodimos and Vera Korelidou and Athanasios Gelasakis and Dimitrios Kalogeras and Anastasios Doulamis and Nikolaos Doulamis},<br>keywords = {Body condition score, Artificial intelligence, Convolutional neural network, Precision livestock farming, Goat, Animal, Signal processing, Computer vision},<br>abstract = {Modern livestock farming systems face the challenge of meeting the growing demand for dairy and meat products while ensuring the well-being of animals. Body Condition Scoring serves as a vital process for assessing the body reserves in animals, impacting their health, welfare, and productivity. However, traditional body condition score (BCS) evaluation methods via observation and palpation of specific anatomical regions are labor-intensive and subjective, hindering their widespread adoption. To address this issue, Precision Livestock Farming (PLF) techniques, particularly those involving Internet of Things (IoT) devices and artificial intelligence (AI), have emerged as promising solutions. In this work, we explore the use of AI, specifically Convolutional Neural Networks (CNNs), to automate the assessment of BCS in goats utilizing imagery data. Our model was trained on 5000 images illustrating the dorsal view of the backside of goats achieving an overall accuracy of 97.94 % which was the highest compared to other popular deep learning architectures from literature (e.g. VGG16, ResNet34, ResNet50, DenseNet, GoogleNet). The proposed custom CNN model for goat-specific BCS estimation overcomes the limitations of manual sketching, providing automatic region identification for BCS assessment. Moreover, it is a lightweight model specifically designed for seamless integration with IoT devices, allowing for efficient on-board processing via cameras. The model's pose-independent nature and adaptability to environmental constraints make it a valuable tool for efficient and sustainable goat farming. This research advances the application of AI as a precision livestock farming tool, contributing to the reinforcement of the animal welfare and productivity, and supporting evidence-based decision-making processes to increase farms' resilience.}<br>}</p>
<p>Anastasios Temenos, Athanasios Voulodimos, Vera Korelidou, Athanasios Gelasakis, Dimitrios Kalogeras, Anastasios Doulamis, Nikolaos Doulamis,<br>Goat-CNN: A lightweight convolutional neural network for pose-independent body condition score estimation in goats,<br>Journal of Agriculture and Food Research,<br>Volume 16,<br>2024,<br>101174,<br>ISSN 2666-1543,<br>https://doi.org/10.1016/j.jafr.2024.101174.<br>(https://www.sciencedirect.com/science/article/pii/S2666154324002114)<br>Abstract: Modern livestock farming systems face the challenge of meeting the growing demand for dairy and meat products while ensuring the well-being of animals. Body Condition Scoring serves as a vital process for assessing the body reserves in animals, impacting their health, welfare, and productivity. However, traditional body condition score (BCS) evaluation methods via observation and palpation of specific anatomical regions are labor-intensive and subjective, hindering their widespread adoption. To address this issue, Precision Livestock Farming (PLF) techniques, particularly those involving Internet of Things (IoT) devices and artificial intelligence (AI), have emerged as promising solutions. In this work, we explore the use of AI, specifically Convolutional Neural Networks (CNNs), to automate the assessment of BCS in goats utilizing imagery data. Our model was trained on 5000 images illustrating the dorsal view of the backside of goats achieving an overall accuracy of 97.94 % which was the highest compared to other popular deep learning architectures from literature (e.g. VGG16, ResNet34, ResNet50, DenseNet, GoogleNet). The proposed custom CNN model for goat-specific BCS estimation overcomes the limitations of manual sketching, providing automatic region identification for BCS assessment. Moreover, it is a lightweight model specifically designed for seamless integration with IoT devices, allowing for efficient on-board processing via cameras. The model's pose-independent nature and adaptability to environmental constraints make it a valuable tool for efficient and sustainable goat farming. This research advances the application of AI as a precision livestock farming tool, contributing to the reinforcement of the animal welfare and productivity, and supporting evidence-based decision-making processes to increase farms' resilience.<br>Keywords: Body condition score; Artificial intelligence; Convolutional neural network; Precision livestock farming; Goat; Animal; Signal processing; Computer vision</p>
HARMONIA: strategy of an integrated resilience assessment platform (IRAP) with available tools and geospatial services
No full textThe huge amount of the available data nowadays has raised some major challenges which are related to the storage, fusion, structure, streaming and processing of these data. In this paper, we present the development of a holistic framework, entitled HARMONIA, that encompasses State-of-The-Art solutions for the emerging issues related to Climate Change, natural and/or man-made hazards and urban/peri-urban risks. The Horizon 2020 HARMONIA project is developing an Integrated Resilience Assessment Platform (IRAP) which plans to provide targeted services for different groups of end-users. In particular, it will actively support urban decision-makers in strategic decisions and planning and citizens in facing daily effects and risks of Climate Change. Additionally, the platform will be a place to interconnect cities which end up facing similar Climate Change effects. HARMONIA IRAP leverages cuttingedge technologies (i.e., explainable Artificial Intelligence, Data Mining, multi-criteria analysis, dynamic programming) and services (ie., Virtual Machines, Containers) in order to provide solutions considering the complexity and diversity of extreme earth and non-earth data. In addition, this platform includes a Decision Support System providing early-warning feedback and recommendations to the end-users. In this way the HARMONIA IRAP design tends to address these challenges by offering the corresponding dynamic, scalable and robust mechanisms with the aim to provide useful integrated tools for the related users. Datacubes architecture, which is a major part of the IRAP, offers the opportunity to investigate more sophisticated correlations among the data and provide a more tangible representation of the extracted information
Optimal recursive similarity measure estimation for interactive content-based image retrieval
No full text
- …
