Research Projects in the area of "Pattern Recognition"
The focus of these collaborative projects is on developing innovative processes for the automated collection, selective recognition and processing of data from different sources, such as cameras and sensors. Improved data analysis can be used to help security personnel assess potentially dangerous situations both at an earlier stage and more accurately. The projects seek preventative solutions, bearing in mind data protection laws in particular as well as social acceptance of the technologies.
Below please find selected research projects. More research projects can be found here http://www.bmbf.de/de/14395.php
Automated detection of situations that require intervention through classification of visual patterns. Cases of violence at bus stops and train stations have resulted in members of the public expressing an urgent need for security and, in some cases, limiting their use of public transport in the late evening or early morning. In many places video cameras have already been installed in underground stations and in rail carriages themselves. However, the sheer number of images alone will not boost security. The ADIS project is working on intelligent solutions in video material analysis to identify precarious situations in specifically designated platform areas. Ideally, for the sake of their own security, passengers can choose to wait in these designated platform areas where such a video camera system is installed. Analysis routines will detect behaviour, gestures and facial expressions that typically lead to threatening situations and, if necessary, sound an alarm.
Digital fingerprints: Although fingerprint analysis has greatly improved in recent years thanks to the use of pattern recognition systems, fingerprint collection is currently an exclusively non-automated process. New approaches will be explored to making fingerprint detection easier and making collection both more extensive and speedier. The objective is to develop a legally compliant system for the time-efficient and automatic collection of fingerprints taken at large-area crime scenes.
Pattern recognition and video tracking - socio-psychological, sociological, ethical and legal analyses. Automated pattern recognition technologies and the implementation of so-called video tracking harbour great potential for providing security personnel with effective support in analysing video surveillance material. Such "intelligent" video systems do, however, raise certain social, ethical and legal issues. These are also addressed in a number of projects that focus on pattern recognition.
Jump directly:
to the main navigation,
to the top of the page
