A modular toolkit for visual tracking performance evaluation
| Autor: | Luka Čehovin Zajc |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
01 natural sciences computer vision Experiment result analysis 03 medical and health sciences Software experiment result analysis 0103 physical sciences Visual tracking 010306 general physics Implementation 030304 developmental biology lcsh:Computer software 0303 health sciences računalniški vid business.industry udc:004.93 vizualno sledenje analiza rezultatov poskusov Modular design visual tracking performance evaluation Computer Science Applications lcsh:QA76.75-76.765 Video tracking Performance evaluation Eye tracking Computer vision State (computer science) ocenjevanje performans Software engineering business Communications protocol Modular software |
| Zdroj: | SoftwareX, Vol 12, Iss, Pp 100623-(2020) SoftwareX, vol. 12, 100623, 2020. |
| ISSN: | 2352-7110 |
| Popis: | We present a modular software package for conducting single-target visual object tracking experiments and analyzing results. Our software supports many of the common usage patterns in visual tracking evaluation out of the box, but is also modular and allows various extensions. Users are able to integrate existing implementations of visual tracking algorithms with little additional effort using a standardized and flexible communication protocol. The software has been the technical backbone of the VOT Challenge initiative for many years and has grown and evolved with the competitions that it supported. We present its current state and the capabilities of the package and conclude with some plans for future development. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|