University of Waterloo

Video Analysis

Video analysis is a field within computer vision that involves the automatic interpretation of digital video using computer algorithms. Although humans are readily able to interpret digital video, developing algorithms for the computer to perform the same task has been highly evasive and is now an active research field. Applications include tracking people who are walking; interpreting actions of moving objects and people; and using the technology to replace the array of screens used in monitoring high risk environments, such as airport security. Fundamental problems in video analysis include denoising, searching for events in video, object extraction (e.g., extract all the people in the scene), scale indifference (e.g. recognizing small trees or large trees, or trees close or far to the camera), reconstructing 3d scene information from video, removing vibration or jitter in the video, and spatially and temporally aligning video captured from multiple cameras. The VIP lab has active research in the field of video analysis.

Related people




Related demos

Action Recognition in Video

Related publications

Journal Articles

Conference Papers