Abstract :
The demand for modular video analytics in surveillance systems is steadily growing as it offers significant advantages when flexibility and/or scalability in terms of computational performance are required. At the same time, the utilization of modular systems raises many questions with regard to ensuring the right for privacy, justice and freedom of citizens when developing and operating surveillance infrastructure. Both, surveillance infrastructure as well as the rights of citizens concerning their personal data are subject to constant change. The socio-ethical nature of individual rights (e.g. the varying perception of such rights) has to be considered too. Last but not least, a concept of accountability (i.e. accountability-by-design) has to be established. Our contribution demonstrates how a set of simple and individually harmless algorithmic modules can be used to obtain sensitive personal information out of surveillance video footage. Trying to solve this challenge solely by technical means (i.e. for individual components) is not expedient and will hardly lead to a successful solution: The functionality of a combination of primitive algorithms can exceed the abilities of the sum of the parts by magnitudes. Strict adherence to the privacy-by-design paradigm for each individual component in order to guarantee privacy preservation for the whole system is not sufficient either. Our solution tackles this challenge on a higher, comprehensive level considering the entire life cycle of surveillance systems, ideally starting with the planning and design phase. It supports the development and ensures that privacy aspects are continuously reviewed whilst the audited system is in operation or maintenance. This indicates another difficulty in connection with the ever-changing nature of the parties being in charge of privacy concerns over the lifetime of surveillance systems. We will present a solution being applied to a surveillance system including modular video analytics using the example of a specific video surveillance scenario.
