Indexing Motion Detection Data for Surveillance Video

Søren Juhl Vind, Philip Bille, Inge Li Gørtz

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

459 Downloads (Pure)


We show how to compactly index video data to support fast motion detection queries. A query specifies a time interval T, a area A in the video and two thresholds v and p. The answer to a query is a list of timestamps in T where ≥ p% of A has changed by ≥ v values. Our results show that by building a small index, we can support queries with a speedup of two to three orders of magnitude compared to motion detection without an index. For high resolution video, the index size is about 20% of the compressed video size.
Original languageEnglish
Title of host publicationProceedings of the IEEE International Symposium on Multimedia (ISM2014)
Number of pages4
PublisherIEEE Press
Publication date2014
ISBN (Print)978-0-7695-5437-2
Publication statusPublished - 2014
EventIEEE International Symposium on Multimedia 2014 - The Splendor Hotel Taichung, Taichung, Taiwan, Province of China
Duration: 10 Dec 201412 Dec 2014
Conference number: 10


ConferenceIEEE International Symposium on Multimedia 2014
LocationThe Splendor Hotel Taichung
Country/TerritoryTaiwan, Province of China
Internet address


  • Motion detection index
  • Motion detection data structure
  • Surveillance video
  • Video analysis
  • Data structure


Dive into the research topics of 'Indexing Motion Detection Data for Surveillance Video'. Together they form a unique fingerprint.

Cite this