You are here

Activity and Scene Analysis

Main activities

We conduct research on vision based gesture recognition, action recognition and activity analysis, with particular emphasis on user-adaptation and the integration with other modalities such as acoustic scene analysis.

Non-invasive technologies for monitoring and understanding complex environments have applications in diverse domains such as security in industrial environment, outdoor and indoor surveillance, person action recognition, traffic analysis, assisted living, customer behaviour, sports analysis etc. This macro-activity is concerned with the development of computer vision technologies for dynamic scene understanding in such applicative contexts. The most recently used techniques are based on machine learning and deep learning with structured output prediction.

Our activities focus on signal processing techniques for detecting user-customized gestures as well as recognising repetitive motion patterns such as occurring during work-out and sport activities.

We apply computer vision monitoring in combination with other sensing modalities (e.g. audio) to explore the relationship between proxemics, visual attention, social signals and personality traits during interaction.

We have developed and field-tested traffic analysis tools for monitoring road intersections and queues. We also apply statistical methods for analyzing complex visual scenes involving people and their activities.

News

From June 30, 2021 the present TeV site (as FBK Drupal web site) is frozen and no longer editable.
On November 30, 2021, the Drupal server will be permanently shut down and this site will be no longer available.

Two Journal papers published on "IEEE Transactions on Pattern Analysis and Machine Intelligence" and on "IEEE Transactions on Multimedia"

Projects

The project develops solutions for identity-preserving tracking in multi-camera environment and tools to facilitate their deployment. Main applications are with real-time people monitoring and behaviour analytics in indoor spaces.

Using a multi-camera setup, TeV contributes to build sport analysis systems by developing video analytics which detect and track in real time players and objects movement in a court.

FITCITY - Promoting a physically active lifestyle through the use of a mobile application that integrates scientifically based fitness assessments and workout routines, gamification techniques, psychological theories and peer-pressure mechanisms.

TRAVEL - Traffic Road Analysis by Visual Event Labelling project is about the automatic analysis of traffic sequences from static or moving cameras, aiming at the detection, classification and tracking of vehicles on the road.

ACUBE - Ambient Aware Assistance develops technologies for monitoring complex environments that can be applied in areas such as assisted living homes to help personnel, as well as to support the independence and safety of users.

PUMALAB - Multimodal Monitoring and Behavior Analysis is to advance the vision-based and audio-visual monitoring of people and their behavior, and to enable the inference of attention patterns as well as of physically observable social signals.

Pages