Scene Segmentation in Adverse Vision Conditions
Semantic road labeling is a key component of systems that aim at assisted or even autonomous driving. Considering that such systems continuously operate in the real-world, unforeseen conditions not represented in any conceivable training procedure are likely to occur on a regular basis. In order to equip systems with the ability to cope with such situations, we would like to enable adaptation to such new situations and conditions at runtime. We study the effect of changing test conditions on scene labeling methods based on a new diverse street scene dataset. We propose a novel approach that can operate in such conditions and is based on a sequential Bayesian model update in order to robustly integrate the arriving images into the adapting procedure.
- 2.Álvarez, J.M., López, A.M.: Road detection based on illuminant invariance. IEEE Trans. on ITS 12(1), 184–193 (2011)Google Scholar
- 4.Dellaert, F., Burgard, W., Fox, D., Thrun, S.: Using the condensation algorithm for robust, vision-based mobile robot localization. In: CVPR (1999)Google Scholar
- 6.Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: NIPS (2011)Google Scholar
- 7.Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: CVPR (2011)Google Scholar