We describe a system for content-based retrieval from large surveillance video archives, using behavior, action and appearance of objects. Objects are detected, tracked, and classified into broad categories. Their behavior and appearance are characterized by action detectors and descriptors, which are indexed in an archive. Queries can be posed as video exemplars, and the results can be refined through relevance feedback. The contributions of our system include the fusion of behavior and action detectors with appearance for matching; the improvement of query results through interactive query refinement (IQR), which learns a discriminative classifier online based on user feedback; and reasonable performance on low resolution, poor quality video. The system operates on video from ground cameras and aerial platforms, both RGB and IR. Performance is evaluated on publicly-available surveillance datasets, showing that subtle actions can be detected under difficult conditions, with reasonable improvement from IQR.

Robots have most successfully been applied in repetitive operations, but often when the task involves complex variable operations in unstructured environments teleoperation is preferred. As the complexity of these human supervisory tasks has increased the trend has been towards greater sensory feedback and more intuitive input control. This paper reports on the relative effectiveness of and need for sensory feedback systems for operator control in telepresence applications. In particular, studies were made of the performance of manipulation and navigation planning operations on a twin armed mobile robot using a variety of visual and audio cues and input systems. The performance was measured by experimentation with a range of subjects at a number of difficulty levels to test the effectiveness of the telepresence controller in a series of technical scenarios.