As video cameras proliferate, the ability to scalably capture and search their data becomes important. Scalability is improved by performing video analytics on cloudlets at the edge of the Internet, and only shipping extracted index information and meta-data to the cloud. In this setting, we describe interactive data exploration (IDE),which refers to human-in-the-loop content-based retrospective search using predicates that may not have been part of any prior indexing. We also describe a new technique called just-in-time indexing (JITI)that improves response times in IDE.

Satyanarayanan, M., Gibbons, P.B., Mummert, L., Pillai, P., Simoens, P., Sukthankar, R.
Proceedings of the IEEE 2017 Global IoT Summit, Geneva, Switzerland, June 2017