KIT | KIT-Bibliothek | Impressum

Efficient Min-cost Flow Tracking with Bounded Memory and Computation

Lenz, Philip

Abstract: This thesis is a contribution to solving multi-target tracking in an optimal fashion for real-time demanding computer vision applications. We introduce a challenging benchmark, recorded with our autonomous driving platform AnnieWAY. Three main challenges of tracking are addressed: Solving the data association (min-cost flow) problem faster than standard solvers, extending this approach to an online setting, and making it real-time capable by a tight approximation of the optimal solution.

Zugehörige Institution(en) am KIT Institut für Mess- und Regelungstechnik mit Maschinenlaboratorium (MRT)
Publikationstyp Hochschulschrift
Jahr 2015
Sprache Englisch
Identifikator DOI(KIT): 10.5445/IR/1000049448
URN: urn:nbn:de:swb:90-494489
KITopen ID: 1000049448
Verlag Karlsruhe
Abschlussart Dissertation
Fakultät Fakultät für Maschinenbau (MACH)
Institut Institut für Mess- und Regelungstechnik mit Maschinenlaboratorium (MRT)
Prüfungsdaten 23.02.2015
Referent/Betreuer Prof. C. Stiller
Bemerkung zur Veröffentlichung This document is licensed under the Creative Commons Attribution - Share Alike 3.0 DE License

(CC BY-SA 3.0 DE):
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page