Multi-GPU based camera network system keeps privacy using growing neural gas

In this work we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events in video. The objectives include: identifying and tracking persons or objects in the scene or the interpretation of user gestures for interaction with services, devices and systems implemented in the digital home. Additionally, the system process several tasks in parallel using GPUs (Graphic Processor Units). Addressing multiple vision tasks of various levels such as segmentation, representation or characterization, analysis and monitoring of the movement to allow the construction of a robust representation of their environment and interpret the elements of the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency and offering relevant information to higher level systems, monitor and take decisions in real time, and must accomplish a set of requirements such as: time constraints, high availability, robustness, high processing speed and re-configurability. Based on our previous work with Growing Neural Gas (GNG) models, we have built a system able to represent and analyze the motion in several image sequences acquired by a multi-camera network and process multisource data in parallel onto a Multi-GPU architecture. The system is able to keep the privacy of the persons under observation by using the graph representation provided by the GNG. Several experiments are presented that demonstrate the validity of the architecture to manage images from different cameras simultaneously.