SafeTrekker: towards automatic recognition of critical situations in mountain excursions

We present preliminary work on the design of a ubiquitous service that could support the participants of outdoor excursions, like trekkers, climbers or ski-mountaineers in identifying potentially dangerous situations as well as to alert with useful information the rescue teams in case of critical conditions. The system is based on a form of privacy preserving crowdsourcing: precise location and sensor-based information is acquired real-time by a trusted system component and can be used in case of emergency, while an anonymized dataset of each excursion is processed by a central component to create a model of "normal" situations. Together with a model of "potentially dangerous" situations created with specific domain knowledge, the system offers a decision support service that can also operate offline on the mobile device of the users.