Efficient Multi-cue Scene Segmentation
- Cite this paper as:
- Scharwächter T., Enzweiler M., Franke U., Roth S. (2013) Efficient Multi-cue Scene Segmentation. In: Weickert J., Hein M., Schiele B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg
This paper presents a novel multi-cue framework for scene segmentation, involving a combination of appearance (grayscale images) and depth cues (dense stereo vision). An efficient 3D environment model is utilized to create a small set of meaningful free-form region hypotheses for object location and extent. Those regions are subsequently categorized into several object classes using an extended multi-cue bag-of-features pipeline. For that, we augment grayscale bag-of-features by bag-of-depth-features operating on dense disparity maps, as well as height pooling to incorporate a 3D geometric ordering into our region descriptor.
In experiments on a large real-world stereo vision data set, we obtain state-of-the-art segmentation results at significantly reduced computational costs. Our dataset is made public for benchmarking purposes.
Unable to display preview. Download preview PDF.