Kitware will be attending and showcasing Computer Vision capabilities at this year’s AVSS 2015!
Come join us this year, at the 12th IEEE International Conference on Advanced Video- and Signal-based Surveillance located at Karlsruhe Institute of Technology & Fraunhofer IOSB, Karlsruhe Germany. This event is the premier annual event showcasing video and signal-based surveillance to advance theories, methods, systems, and applications. The event brings in attendance world-wide with experts from academia, industry, and government.
Kitware’s participation this year includes:
- Invited talk at the 3rd Workshop on Vehicle Retrieval in Surveillance.
- Kitware Company Show-Case at the 2nd Annual Surveillance Day, August 26 2015.
- An oral presentation in the main conference, Friday August 28, 15:45. ‘An End-to-End System for Content-Based Retrieval using Behavior, Actions, and Appearance with Interactive Query Refinement.’ Presented by Roddy Collins.
- Abstract: 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.
User interface allows analyst to query a particular video selection and find other instances that match it. This cuts down on analysts time and effort needed to search through video for appearance, actions, and behaviors of interest.
Stay tuned for more information as we get closer to the event date! We look forward to see you there!
Please visit our Computer Vision webpage for more information!