Tracking Multiple People Online and in Real Time
Abstract
We cast the problem of tracking several people as a graph partitioning problem that takes the form of an NP-hard binary integer program. We propose a tractable, approximate, online solution through the combination of a multistage cascade and a sliding temporal window. Our experiments demonstrate significant accuracy improvement over the state of the art and real-time post-detection performance.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 21, 2015
- Accession Number
- ADA631602
Entities
People
- Carlo Tomasi
- Ergys Ristani
Organizations
- Duke University