University of Twente Student Theses
Anomaly detection in defence and surveillance
Sybenga, S.D.A (2016) Anomaly detection in defence and surveillance.
|
PDF
9MB |
| Abstract: | Modern surveillance systems such as satellites and drones are capable of capturing wide areas with high precision. This provides the ability to find and track people on the streets. The gathered information can be shown to operators, who have to constantly analyze the data and decide if there are suspicious events occurring in the covered area. In big areas such as cities, this is searching for a needle in a haystack. Automated anomaly detection can help an operator to find suspicious behavior and respond accordingly. An anomaly detection technique based on different contexts, features and models is proposed and used in a prototype detection system. Evaluation is done using a simulator, which can generate normal situations as well as anomalous events such as a procession, street theft and commercial robbery. |
| Item Type: | Essay (Master) |
| Clients: | Alten Nederland TNO |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Interaction Technology MSc (60030) |
| Link to this item: | https://purl.utwente.nl/essays/70757 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page