Citation

Vazquez D, López AM, Marin J, Ponsa D, Gerónimo D. IEEE Trans. Pattern Anal. Mach. Intell. 2013; ePub(ePub): ePub.

Affiliation

Universitat Autònoma de Barcelona (UAB) Computer Vision Center (CVC), Bellaterra Bellaterra.

Copyright

(Copyright © 2013, Institute of Electrical and Electronics Engineers, Publisher IEEE (Institute of Electrical and Electronics Engineers))

DOI

01C55106-D14F-4365-A376-31978AFCCBAC

PMID

23979065

Abstract

Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?. Conducted experiments show that virtual-world based training can provide excellent testing performance in real world, but it can also suffer the dataset shift problem as real-world based training does. Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. V-AYLA reports the same detection performance than when training with many human-provided pedestrian annotations and testing with real-world images of the same domain. To the best of our knowledge, this is the first work demonstrating adaptation of virtual and real worlds for developing an object detector.

Language: en