This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Virtual and Real World Adaptationfor Pedestrian Detection
April 2014 (vol. 36 no. 4)
pp. 797-809
Javier Marín, Centro de Vision Por Computador-Edificio O, Univ. Autonoma de Barcelona, Bellaterra, Spain
Daniel Ponsa, Centro de Vision Por Computador-Edificio O, Univ. Autonoma de Barcelona, Bellaterra, Spain
David Gerónimo, Centro de Vision Por Computador-Edificio O, Univ. Autonoma de Barcelona, Bellaterra, Spain
Antonio M. Lopez, Centro de Vision Por Computador-Edificio O, Univ. Autonoma de Barcelona, Bellaterra, Spain
David Vázquez, Centro de Vision Por Computador-Edificio O, Univ. Autonoma de Barcelona, Bellaterra, Spain
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 real-world images? Conducted experiments show that virtual-world based training can provide excellent testing accuracy in real world, but it can also suffer the data set 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 accuracy 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.
Index Terms:
Training,Detectors,Testing,Accuracy,Cameras,Image resolution,Interpolation,domain adaptation,Pedestrian detection,photo-realistic computer animation,data set shift
Citation:
Javier Marín, Daniel Ponsa, David Gerónimo, Antonio M. Lopez, David Vázquez, "Virtual and Real World Adaptationfor Pedestrian Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 4, pp. 797-809, April 2014, doi:10.1109/TPAMI.2013.163
Usage of this product signifies your acceptance of the Terms of Use.