We are happy to announce the seven workshops will take place in conjunction with the AVSS at August 29th, 2017 at Patria Palace Hotel (one day before the main conference program):
- International Workshop on Traffic and Street Surveillance for Safety and Security (IWT4S).
Big city centers are subjected to a growing amount of people and vehicle mobility, making the control and security management increasingly difficult.
In the last decades, there has been a dramatic increase in demand for smart systems capable of monitoring traffic and street safety and automatically detect possible problems (accidents, traffic jam, brawls…) in order to elicit and support the intervention of law enforcement agencies or medical staff.
It is goal of this Workshop to provide a comprehensive evaluation to state-of-the-art on systems devoted to city and traffic security.
The workshop will be held in conjunction with the Challenge on Advanced Traffic Monitoring, a challenge devoted to the improvement of vehicle detection and tracking algorithms.
Organizers: Marco Del Coco: Institute of Applied Sciences and Intelligent Systems, CNR, Italy (firstname.lastname@example.org) Siwei Lyu: University at Albany, USA (email@example.com); Pierluigi Carcagnì Institute of Applied Sciences and Intelligent Systems, CNR, Italy (firstname.lastname@example.org) Ming-Ching Chang University at Albany, USA Ser-Nam Lim GE Global Research Center, USA Honggang Qi University of Chinese Academy of Sciences, China (email@example.com).
- Analysis of video and audio “in the Wild”: addressing real-world data sources to support the fight against crime and terrorism.
This workshop focuses on the investigation of novel approaches for analysis of video and audio to support the security forces in the process of crime solving and prevention targeting real-world challenging data sources.
The goal is to present revisited and novel algorithms that show resilience when applied to challenging real content from CCTV, hard drives or online resources (e.g. YouTube). Only papers describing related techniques with solid evidence of the use and validation in video and audio “in the Wild” will be presented.
The objective is to draw researcher’s attention to emerging strategies that are robust against the real challenges to be addressed when technologies developed in a laboratory environment are deployed in practice. To this end we will present each accepted paper with the opportunity to showcase their approach via a practical demonstration of how it could be used in practice during a dedicated demo session organized as part of the workshop.
- International workshop on small-drone surveillance, detection and counteraction techniques (WOSDETC).
In the last few years the popularity of small Remotely Piloted Aircraft Systems (RPAS), commonly called just “drones”, has exponentially increased due to the widespread availability of low-cost off-the-shelf products, including build-from-scratch and DIY kits. At the same time, issues regarding safety, privacy and security aspects are progressively arising. There is actually a gap in current surveillance systems for the detection of such flying systems, which can be used for illegal activities such as smuggling of drugs or espionage, as well as for carrying explosives or chemical weapons. Their low cost and very small radar signature is thus making them, unfortunately, a favorite platform for terrorists.
Several surveillance and detection technologies are under investigation at the moment, including LIDAR, passive acoustic sensors, passive radio detection and video analytics. However, several challenges must be faced to lower the probability of false alarm, increase the surveillance range and detection rate, as well as to promptly put into action the most appropriate countermeasures according to the operating scenario.
Organizer: Angelo Coluccia: Department of Innovation Engineering, University of Salento, Lecce, Italy (firstname.lastname@example.org).
- Smart Indoor Event and Activity Recognition Workshop (SIEARW).
With the advent of the Internet of Things and the boost of Data Sciences, new challenges arise in human activity analysis, as well as a vast range of applications, especially in the domain of indoor environments. However, even if sensing devices (e.g. cameras, depth sensors, wearable devices, web access points) and computational power have improved significantly in the last years, the most promising algorithms for human activity analysis and event prediction are constrained by limited datasets, usage contexts, physical obstacles, personalized patterns of behaviors, etc. Another big challenge in data analysis and efficient application of machine learning arises from the fact that indoor environments impose problems related to sensor noise, scene clutter and false alarms attributed to contextual constraints.
The scope of this workshop is to bring together researchers and developers working in the area of human activity analysis and event prediction in indoor environments and present state-of-the-art techniques and results in different domains where surveillance can bring major societal impact (health, security, resource management, building space management, etc.). The workshop will leverage results from the ICT4Life EU funded project and it will welcome research contributions from the broader research community.
Organizers: Stylianos (Stelios) Asteriadis, University of Maastricht (email@example.com); Mirela Popa, University of Maastricht (firstname.lastname@example.org); Petros Daras, Centre for Research and Technology, Hellas (email@example.com); Federico Álvarez, Universidad Politecnica de Madrid (firstname.lastname@example.org).
- Signal Processing for Understanding Crowd Dynamics (SP-CROWD)
Nowadays, the increased demand of security is a particularly relevant need of our society. Therefore, systems able to automatically interpret interactions, both among people and between people and the environment, represent an actual domain of research which still lack efficient solutions and open problems.
This symposium will reflect current state-of-the-art approaches for crowded environments understanding, with a strong focus on the signal processing perspective. In particular, contributions related to integration in intelligent systems, cognitive dynamic algorithms, bio-inspired techniques, crowded environment interactions modeling and simulation, are expected. Novel contributions will be highly encouraged dealing with the crowd understanding phenomenon through innovative methodologies based, for instance, on graph signal processing, deep learning, big data analysis, convolutional neural networks, compressive sensing, multimedia and multi-modal analysis.
Organizers: Lucio Marcenaro, Department of Electrical, Electronic, Telecommunications Engineering and Naval Architecture (DITEN) University of Genova (email@example.com); Nicola Conci, Dipartimento di Ingegneria e Scienza dell’Informazione, University of Trento (firstname.lastname@example.org); Peter Tu, GE Global Research (email@example.com), Eduardo Monari, Fraunhofer IOSB (firstname.lastname@example.org).
The growing number of surveillance cameras spread over the territory, as well as the increasing number of mobile devices able to acquire images, video streams or just speed and position, such as smartphones or wearable devices, has lead in the last decades to an increasing interest of the scientific community towards those solutions able to automatically analyse the scene where a person is moving so as to identify events of interest . This interest has been accompanied by a strong pushing of the market, more and more interested in the possibility to run the above algorithms directly on board of cameras, smartphones and wearable devices, or more generally on board of embedded low-cost architectures .
Within this context, the scientific problem, addressed by this workshop, becomes to find out the best possible trade-off between the accuracy required by the particular application at hand and the computational burden needed for its computation . The combination between computer vision algorithms and embedded systems is typically referred to as “Embedded Vision ”.
Organizers: Alessia Saggese, University of Salerno (email@example.com); Mario Vento, University of Salerno (firstname.lastname@example.org); Luca Greco, University of Salerno (email@example.com); Brian C. Lovell, The University of Queensland, Australia (firstname.lastname@example.org).
Environmental monitoring and data analysis across expansive environments for surveillance and security applications gain significant support from the integration of robotics and sensor network technologies. In particular, robots can augment the capabilities of stationary sensor networks offering increased availability and awareness, as compared to a static system. Pattern recognition and machine learning play a key role for analysis and interpretation of the data acquired by robot/sensor systems, enabling observation, modeling and understanding of environmental targets, towards the development of intelligent systems for effective detection and monitoring of security, health, and resource management issues.
This full-day workshop intends to bring together researchers and practitioners with various backgrounds relevant to this multidisciplinary field of research, namely researchers from field robotics, sensors and sensor networks for security and surveillance, visual and signal-based monitoring systems, environmental data processing, classification, pattern recognition, computer vision, communications in monitoring systems, sea monitoring, agricultural and forest monitoring.
Organizers: Rosalia Maglietta, CNR-ISSIA (email@example.com); Annalisa Milella, CNR-ISSIA (firstname.lastname@example.org); Shahriar Negahdaripour, University of Miami (email@example.com); Giulio Reina, Università del Salento (firstname.lastname@example.org); Carmelo Fanizza, Jonian Dolphin Conservation (email@example.com).