Chanwut (Mick) Kittivorawong, student of BIDS Faculty Affiliate Alvin Cheung, led a seminar recently at which he featured his work on Spatialyze, a new framework for end-to-end querying of geospatial videos.
Spatialyze comes with a domain-specific language where users can construct geospatial video analytic workflows using a 3-step, declarative, build-filter-observe paradigm. Internally, Spatialyze leverages the declarative nature of such workflows, the temporal-spatial metadata stored with videos, and physical behavior of real-world objects to optimize the execution of workflows. Our results using real-world videos and workflows show that Spatialyze can reduce execution time by up to 5.3x, while maintaining up to 97.1% accuracy compared to unoptimized execution.
Chanwut described the workflow, optimization techniques, and some intriguing results.
This work is ongoing and he's looking for new users - get in touch!
