This is not the latest version of this item. The latest version can be found here.
MIRIS: Fast Object Track Queries in Video
Name
miris-sigmod.pdf
Description
Accepted version
Size
6.78 MB
Format
Adobe PDF
Checksum (MD5)
45e092f04b6c32c2b2e79be52ec41d6a
Author(s)
Bastani, Favyen
He, Songtao
Balasingam, Arjun
Gopalakrishnan, Karthik
Alizadeh, Mohammad
Balakrishnan, Hari
Cafarella, Michael
Kraska, Tim
Madden, Sam
Journal
Proceedings of the ACM SIGMOD International Conference on Management of Data
Publisher
ACM
Version
Author's final manuscript
Abstract
© 2020 Association for Computing Machinery. Video databases that enable queries with object-track predicates are useful in many applications. Such queries include selecting objects that move from one region of the camera frame to another (e.g., finding cars that turn right through a junction) and selecting objects with certain speeds (e.g., finding animals that stop to drink water from a lake). Processing such predicates efficiently is challenging because they involve the movement of an object over several video frames. We propose a novel query-driven tracking approach that integrates query processing with object tracking to efficiently process object track queries and address the computational complexity of object detection methods. By processing video at low framerates when possible, but increasing the framerate when needed to ensure high-accuracy on a query, our approach substantially speeds up query execution. We have implemented query-driven tracking in MIRIS, a video query processor, and compare MIRIS against four baselines on a diverse dataset consisting of five sources of video and nine distinct queries. We find that, at the same accuracy, MIRIS accelerates video query processing by 9x on average over the IOU tracker, an overlap-based tracking-by-detection method used in existing video database systems.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1145/3318464.3389692
