A5075830042- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Fire Detection and Safety Systems
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Context-Aware Activity Recognition Systems
- Evacuation and Crowd Dynamics
- Gait Recognition and Analysis
- Flood Risk Assessment and Management
- UAV Applications and Optimization
- Advanced Image and Video Retrieval Techniques
- COVID-19 diagnosis using AI
- Complex Network Analysis Techniques
- Hand Gesture Recognition Systems
- Bacillus and Francisella bacterial research
- Non-Destructive Testing Techniques
- Speech and Audio Processing
- Data-Driven Disease Surveillance
- Digital Media Forensic Detection
- Automated Road and Building Extraction
- Robotics and Sensor-Based Localization
- Technology and Security Systems
- Robotics and Automated Systems
- Hearing Impairment and Communication
- Misinformation and Its Impacts
Information Technologies Institute
2017-2024
Centre for Research and Technology Hellas
2017-2024
Social media play an important role in the daily life of people around globe and users have emerged as active part news distribution well production. The threatening pandemic COVID-19 has been lead subject online discussions posts, resulting to large amounts related social data, which can be utilised reinforce crisis management several ways. Towards this direction, we propose a novel framework collect, analyse, visualise Twitter tailored specifically monitor virus spread severely affected...
Motivated by the increasing industry trends towards autonomous driving, vehicles, and transportation we focus on developing a traffic analysis framework for automatic exploitation of large pool available data relative to applications. We propose cooperative detection tracking algorithm retrieval vehicle trajectories in video surveillance footage based deep CNN features that is ultimately used two separate modalities: (a) speed estimation state art fully camera calibration (b) possibly...
This paper presents a novel warning system framework for detecting people and vehicles in danger. The was tested several images compiled from Flickr other social media sources is highly suggested to get integrated future surveillance safety systems preventing or solving crisis events. proposed recruits State-of-the-Art deep learning technologies so as solve series of image processing machine challenges provides near real-time localization solution scoring severity levels flood fire images.
The analysis of dynamic scenes in video is a very useful task especially for the detection and monitoring natural hazards such as floods fires. In this work, we focus on challenging problem real-world scene understanding, where videos contain textures that have been recorded "wild". These feature large illumination variations, complex motion, occlusions, camera well significant intra-class differences, motion patterns same category may be subject to variations real world recordings. We...
A novel work for Ambient Assisted Living applications is presented here. More specifically, this paper focuses on activity recognition from recordings of daily living captured by wearable cameras. It constructs a discriminant object centric motion descriptor representing the micro-actions within viewpoint action maker so as to later define that he/she performs. The accumulation these activities build patterns over time can be used study behavior end-users, which very useful health...
Unexploded Ordnance (UXO) classification is a challenging task which currently tackled using electromagnetic induction devices that are expensive and may require physical presence in potentially hazardous environments. The limited availability of open UXO data has, until now, impeded the progress image-based classification, offer safe alternative at reduced cost. In addition, existing sporadic efforts focus mainly on small scale experiments only subset common categories. Our work aims to...