A5045224831- Video Surveillance and Tracking Methods
- Face and Expression Recognition
- Face recognition and analysis
- Target Tracking and Data Fusion in Sensor Networks
- Autism Spectrum Disorder Research
- Gaze Tracking and Assistive Technology
- Advanced Neural Network Applications
- Social Robot Interaction and HRI
- Advanced Image and Video Retrieval Techniques
- Emotion and Mood Recognition
- Infrared Target Detection Methodologies
- Assistive Technology in Communication and Mobility
- Water Quality Monitoring Technologies
- Industrial Vision Systems and Defect Detection
- Underwater Acoustics Research
- Anomaly Detection Techniques and Applications
- Distributed Sensor Networks and Detection Algorithms
- Child Development and Digital Technology
- IoT-based Smart Home Systems
- Air Quality Monitoring and Forecasting
- Human Mobility and Location-Based Analysis
- Image Processing Techniques and Applications
- Digital Holography and Microscopy
- Radar Systems and Signal Processing
- Welding Techniques and Residual Stresses
National Research Council
2014-2024
Institute of Applied Science and Intelligent Systems
2023
University of Salento
2012-2017
Innovation Engineering (Italy)
2012
Automatic facial expression recognition (FER) is a topic of growing interest mainly due to the rapid spread assistive technology applications, as human-robot interaction, where robust emotional awareness key point best accomplish task. This paper proposes comprehensive study on application histogram oriented gradients (HOG) descriptor in FER problem, highlighting this powerful technique could be effectively exploited for purpose. In particular, highlights that proper set HOG parameters can...
The rapid advances of transportation infrastructure have led to a dramatic increase in the demand for smart systems capable monitoring traffic and street safety. Fundamental these applications are community-based evaluation platform benchmark object detection multi-object tracking. To this end, we organize AVSS2017 Challenge on Advanced Traffic Monitoring, conjunction with International Workshop Street Surveillance Safety Security (IWT4S), evaluate state-of-the-art tracking algorithms...
Alzheimer’s disease (AD) is the most common form of dementia. Computer-aided diagnosis (CAD) can help in early detection associated cognitive impairment. The aim this work to improve automatic dementia MRI brain data. For purpose, we used an established pipeline that includes registration, slicing, and classification steps. contribution research was investigate for first time, our knowledge, three current promising deep convolutional models (ResNet, DenseNet, EfficientNet) two...
Autism Spectrum Disorders (ASD) are a group of lifelong disabilities that affect people's communication and understanding social cues. The state the art witnesses how technology, in particular robotics, may offer promising tools to strengthen research therapy ASD. This work represents first attempt use machine-learning strategies during robot-ASD children interactions, terms facial expression imitation, making possible an objective evaluation children's behaviours then giving possibility...
Information and communication technologies (ICTs) have been proved to a great impact in enhancing social, communicative, language development children with autism spectrum disorders (ASDs) as demonstrated by plenty of effective technological tools reported the literature for diagnosis, assessment, treatment such neurological diseases. On contrary, there are very few works exploiting ICT study mechanisms that trigger behavioral patterns during specialized sessions focused on social...
It has been proved that Autism Spectrum Disorders (ASD) are associated with amplified emotional responses and poor control. Underlying mechanisms characteristics of these difficulties in using, sharing responding to emotions still not understood. This is because advanced computational approaches for studying details facial expressions have based on the use invasive instruments (such markers motion capture or Electromyographs) can affect behaviors and, above all, restrict possibility...
This paper presents a detailed study about different algorithmic configurations for estimating soft biometric traits. In particular, recently introduced common framework is the starting point of study: it includes an initial facial detection, subsequent traits description, data reduction step, and final classification step. The are featured by descriptors strategies to build training dataset scale in input classifier. Experimental proofs have been carried out on both publicly available...
The management of water resources is becoming increasingly important in several contexts, including agriculture. Recently, innovative agricultural practices, advanced sensors, and Internet Things (IoT) devices have made it possible to improve the efficiency use. However, application control strategies based on machine learning techniques that enables adoption smart irrigation scheduling immediate economic, social, environmental benefits. This challenging research area has attracted attention...
Computer vision is a powerful tool for healthcare applications since it can provide objective diagnosis and assessment of pathologies, not depending on clinicians’ skills experiences. It also help speed-up population screening, reducing health care costs improving the quality service. Several works summarise systems in medical imaging, whereas less work devoted to surveying approaches goals using ambient intelligence, i.e., observing individuals natural settings. Even more, there lack papers...
In the present paper, we focus on design of a Kalman-based algorithm to track single target in range. The proposed approach exploits spillover energy between consecutive matched filter samples; this end, at <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> th scan, GLRT-based detector is fed by predicted position (computed tracker using measurements up ( -1)th scan) and returns an estimate current (measurement) obtained taking into account...
Abstract In thiswork, a real-time system able to automatically recognize soft-biometric traits is introduced and used improve the capability of humanoid robot interact with humans. particular proposed estimate gender age humans in images acquired from embedded camera robot. This knowledge allows properly react customized behaviors related gender/age interacting individuals. The handle multiple persons same image, recognizing each person robot’s field view. These features make particularly...
Deep Learning has becoming a popular and effective way to address large set of issues. In particular, in computer vision, it been exploited get satisfying recognition performance unconstrained conditions. However, this wild race towards even better extreme conditions overshadowed an important step i.e. the assessment impact new methodology on traditional issues which for years researchers had worked. This is particularly true biometrics applications where evaluation deep learning made...
This work presents a system for the automatic analysis of facial expressions. The is completely unobtrusive (nothing to wear, no calibration required) and it takes as input video sequences acquired from off-the-shelf devices (e.g., webcam). A computer vision module, made up by three main components aiming at landmark detection tracking, action unit extraction expression assessment respectively, processes images an onthe-shelf camera. paper demonstrates system's potential in analysing...
The complexity of multi-target tracking grows faster than linearly with the increase numbers objects, thus making design real-time trackers a challenging task for scenarios large number targets. Probability Hypothesis Density (PHD) filter is known to help reducing this complexity. However, reduction may not suffice in critical situations when targets, dimension state vector, clutter conditions and sample rate are high. To address problem, we propose parallelization scheme particle PHD...
The lentil (Lens culinaris Medik.) is one of the major pulse crops cultivated worldwide. However, in last decades, cultivation has decreased many areas surrounding Mediterranean countries due to low yields, new lifestyles, and changed eating habits. Thus, landraces local varieties have disappeared, while farmers are only custodians treasure genetic resources. Recently, been rediscovered meet needs more sustainable agriculture food systems. Here, we proposed an image analysis approach that,...