Current development of security sensor networks and their pro- cessing algorithms use pre-recorded or abstract data streams for testing, often missing important ground truth for validation. This paper proposes a simula- tion-based test bed, presenting an approach to use commercial off the shelf vir- tual reality environments to create adaptive simulations of sensors, data streams and scenarios for training and testing perceptive algorithms. An example using airborne visual multi object tracking is discussed and validated. «
Current development of security sensor networks and their pro- cessing algorithms use pre-recorded or abstract data streams for testing, often missing important ground truth for validation. This paper proposes a simula- tion-based test bed, presenting an approach to use commercial off the shelf vir- tual reality environments to create adaptive simulations of sensors, data streams and scenarios for training and testing perceptive algorithms. An example using airborne visual multi object tracking... »