MAVVSTREAM: EXPRESSING AND PROCESSING SITUATIONS ON VIDEOS USING THE STREAM PROCESSING PARADIGM
Image and Video Analysis (IVA) has been ongoing for several decades and
has come up with impressive techniques for object identification, re-identification,
activity detection etc. A large number of techniques have been developed and used
for processing video frames to detect objects and situations from videos. Camera
angles, lighting effect, color differences, and attire make it difficult to analyze videos.
Several approaches for searching, and querying videos and images have been developed
using indexing and other techniques. This thesis takes a novel approach by converting
a video (through extraction of its contents) into a representation over which queries
can be specified. This is similar to querying a relational database but on contents
extracted from a video and represented using a richer data model. This thesis focuses
on new operators needed and their relevance to express real-world situations, such as
Alert if the same person came through the same door n times within an hour. model
that is needed for representing extracted video contents. The long-term goal is to
significantly augment the image and video analysis capabilities for querying.