PT Unknown AU Yainuvis Socarras Sebastian Ramos David Vazquez Antonio Lopez Theo Gevers TI Adapting Pedestrian Detection from Synthetic to Far Infrared Images BT ICCV Workshop on Visual Domain Adaptation and Dataset Bias PY 2013 LA English DE Domain Adaptation; Far Infrared; Pedestrian Detection AB We present different techniques to adapt a pedestrian classifier trained with synthetic images and the corresponding automatically generated annotations to operate with far infrared (FIR) images. The information contained in this kind of images allow us to develop a robust pedestrian detector invariant to extreme illumination changes. PI Sydney, Australy ER