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. |
Year | DOI | Venue |
---|---|---|
2014 | 01C55106-D14F-4365-A376-31978AFCCBAC | IEEE transactions on pattern analysis and machine intelligence |
Keywords | Field | DocType |
pedestrians,data set shift,realistic virtual worlds,virtual reality,domain adaptation framework,pedestrian detection,learning (artificial intelligence),pedestrian samples,photo-realistic computer animation,object detector,source domain,domain adaptation,pedestrian appearance model,target domain,image classification,virtual-world based training,v-ayla,object detection,adapted pedestrian classifier,human-provided pedestrian annotations,real-world images | Computer vision,Metaverse,Object detection,Virtual reality,Computer science,Active appearance model,Artificial intelligence,Contextual image classification,Classifier (linguistics),Pedestrian detection,Machine learning,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
36 | 4 | 1939-3539 |
Citations | PageRank | References |
53 | 1.96 | 29 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
David Vázquez | 1 | 488 | 28.04 |
Antonio M. López | 2 | 739 | 54.13 |
Javier Marín | 3 | 53 | 1.96 |
Daniel Ponsa | 4 | 219 | 16.99 |
David Gerónimo Gómez | 5 | 53 | 1.96 |