Foundations for Summarizing and Learning Latent Structure in Video
Video data from a variety of DoD platforms is proliferating in the modern battlespace, and expanded dissemination of this video makes it widely available. However, the detection of artifacts of interest in streaming surveillance video is a manually intensive process. As the volume of video data continues to increase, automated video summarization that highlights artifacts of interest is needed. In this work, we are developing automated and semantically meaningful video summarization and sense making to improve situational awareness, reduce the amount of manual processing necessary, and increase the volume of video data that can be analyzed in near real-time.