Traditional event detection from video frames are based on a batch or offline based algorithms: it is assumed that a single event is present within each video, and videos are processed, typically via a pre-processing algorithm which requires enormous amounts of computation and takes lots of CPU time to complete the task. While this can be suitable for tasks which have specified training and testing phases where time is not critical, it is entirely unacceptable for some real-world applications which require a prompt, real-time event interpretation on time. With the recent success of using multiple models for learning features such as generative adversarial autoencoder (GANS), we propose a two-model approach for real-time detection. Like GANs which learns the generative model of the dataset and further optimizes by using the discriminator which learn per sample difference between generated images. The proposed architecture uses a pre-trained model with a large dataset which is used to boost weekly labeled instances in parallel with deep-layers for the small aerial targets with a fraction of the computation time for training and detection with high accuracy. We emphasize previous work on unsupervised learning due to overheads in training labeled data in the sensor domain.
Research in advanced surveillance systems concepts is actively being pursued throughout DoD. One flexible and cost effective way of evaluating the mission effectiveness of these system concepts is through the use of mission level simulations. This approach enables the warfighter to “test drive” systems in their intended environment, without consuming time and money building and testing prototypes. On the other hand, due to the size and complexity of mission level simulations, the sensor modeling capability can be limited, to the point that significantly different system designs appear indistinguishable. To overcome this we have developed a meta-model approach which permits integrating most of the fidelity of radar engineering tools into mission-level simulations without significantly impacting the timeliness of the simulation. In this paper we introduce the SensorCraft concept and the engineering and mission level simulation tools that were employed to develop and model the concept. Then we present our meta model designs and show how they improve the fidelity of the mission level simulation.