KIT | KIT-Bibliothek | Impressum | Datenschutz

Deep Classification-driven Domain Adaptation for Cross-Modal Driver Behavior Recognition

Reiß, Simon; Roitberg, Alina; Haurilet, Monica; Stiefelhagen, Rainer

Abstract (englisch):
We encounter a wide range of obstacles when integrating computer vision algorithms into applications inside the vehicle cabin, eg variations in illumination, sensor-type and-placement. Thus, designing domain-invariant representations is crucial for employing such models in practice. Still, the vast majority of driver activity recognition algorithms are developed under the assumption of a static domain, ie an identical distribution of training-and test data. In this work, we aim to bring driver monitoring to a setting, where domain shifts can occur at any time and explore generative models which learn a shared representation space of the source and target domain. First, we formulate the problem of unsupervised domain adaptation for driver activity recognition, where a model trained on labeled examples from the source domain (ie color images) is intended to adjust to a different target domain (ie infrared images) where only unlabeled data is available during training. To address this problem, we leverage current progress in imageto-image translation and adopt multiple strategies for learning a joint latent space of the source and target distribution and a mapping function to the domain of interest. ... mehr

Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator KITopen-ID: 1000126799
Erschienen in 31st IEEE Intelligent Vehicles Symposium (2020)
Veranstaltung 31st IEEE Intelligent Vehicles Symposium (2020), Online, 19.10.2020 – 13.11.2020
Bemerkung zur Veröffentlichung Die Veranstaltung fand wegen der Corona-Pandemie als Online-Event statt.
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page