A5018232804- Hand Gesture Recognition Systems
- Hearing Impairment and Communication
- Human Pose and Action Recognition
- Gait Recognition and Analysis
- linguistics and terminology studies
- Remote Sensing in Agriculture
- Robot Manipulation and Learning
- Diet and metabolism studies
- Plant and animal studies
- Time Series Analysis and Forecasting
- Nutritional Studies and Diet
- Artificial Intelligence in Healthcare and Education
- 3D Shape Modeling and Analysis
- Spectroscopy and Chemometric Analyses
- Smart Agriculture and AI
- Botulinum Toxin and Related Neurological Disorders
- Image Processing and 3D Reconstruction
- Cerebral Palsy and Movement Disorders
- Insect and Pesticide Research
- Data Stream Mining Techniques
- Parkinson's Disease Mechanisms and Treatments
- Topic Modeling
- 3D Surveying and Cultural Heritage
- Bee Products Chemical Analysis
Information Technologies Institute
2020-2024
Centre for Research and Technology Hellas
2020-2024
Democritus University of Thrace
2018
In this paper, a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted. By implementing the most recent deep neural network in field, thorough evaluation on multiple publicly available datasets performed. The aim present study to provide insights recognition, focusing mapping non-segmented video streams glosses. For task, two new sequence training criteria, known from fields speech and scene text are introduced. Furthermore, plethora...
The field of 3D hand pose estimation has been gaining a lot attention recently, due to its significance in several applications that require human-computer interaction (HCI). utilization technological advances, such as cost-efficient depth cameras coupled with the explosive progress Deep Neural Networks (DNNs), led significant boost development robust markerless methods. Nonetheless, finger occlusions and rapid motions still challenges accuracy In this survey, we provide comprehensive study...
In recent years the availability of satellite image observations Earth has been increasing, creating opportunities for automated methods to be applied in tasks with significant economic importance, such as agricultural parcel crop classification. Designing and implementing that can efficiently interpret images handle their temporal nature poses a challenge remote sensing. Deep learning models have proven able leverage these type data, taking into consideration both spatial well nature....
Honey bees play an essential role in the food chain, being responsible for one third of global supply due to pollination. Thus, preserving health beehives is paramount environmental and economic importance. Unfortunately, at present a decline bee populations reported, attributed factors such as climate change, disasters, use pesticides, etc. The SmartBeeKeep (https://smartbeekeep.eu/) research project, co-funded by EU Greek funds, builds on latest developments remote sensing AI technologies...
In this paper, we propose a novel multi-stage deep learning methodology to accurately tackle the problem of hand pose estimation. More specifically, initially disentanglement stage differentiate significant pose-specific information from irrelevant background noise and illumination variations RGB images. Then, introduce variational alignment align latent spaces true information, effectively improving discrimination ability proposed methodology. Finally, use two loss terms impose...
Parkinson's disease (PD), the second most prevalent neurodegenerative condition, lacks a cure, but its symptoms can be managed. Its complex diagnosis and assessment need ongoing monitoring, highlighting potential use of digital tools for enhancing patient management, even outside clinical settings. In this vein, paper proposes smartphone-based video analysis approach assessing motor skills, particularly balance posture, in individuals diagnosed with PD. particular, Movement Disorder Society...
The accelerated advancements in remote sensing technologies and the deployment of satellites offering freely accessible multispectral satellite imagery have facilitated application machine learning, particularly deep learning techniques, to tasks such as crop classification, yield estimation, bloom detection. Additionally, several countries European Union adopted Land Parcel Identification System (LPIS), that obliges farmers declare exact area type their parcels each year while also making...