Efficient Multi-cue Scene Segmentation

@inproceedings{Scharwchter2013EfficientMS,
  title={Efficient Multi-cue Scene Segmentation},
  author={Timo Scharw{\"a}chter and M. Enzweiler and Uwe Franke and S. Roth},
  booktitle={GCPR},
  year={2013}
}
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… Expand
62 Citations
Object-Level Priors for Stixel Generation
  • 18
  • PDF
Stixel based scene understanding for autonomous vehicles
  • 3
  • PDF
Layered Interpretation of Street View Images
  • 15
  • PDF
Geodesic pixel neighborhoods for 2D and 3D scene understanding
  • 6
  • Highly Influenced
  • PDF
Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding
  • 58
  • PDF
Semantic Urban Maps
  • 2
Simultaneous Transparent and Non-Transparent Object Segmentation With Multispectral Scenes
  • 2
Ground segmentation and occupancy grid generation using probability fields
  • 11
  • Highly Influenced
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
  • 395
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
Semantic segmentation of street scenes by superpixel co-occurrence and 3D geometry
  • B. Micusík, J. Kosecka
  • Mathematics, Computer Science
  • 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops
  • 2009
  • 77
  • PDF
Combining Appearance and Structure from Motion Features for Road Scene Understanding
  • 220
  • PDF
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
  • S. Lazebnik, C. Schmid, J. Ponce
  • Computer Science
  • 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
  • 8,109
  • Highly Influential
  • PDF
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
  • 488
  • PDF
A textured object recognition pipeline for color and depth image data
  • 122
  • PDF
Semantic segmentation using regions and parts
  • 285
  • PDF
Semantic Segmentation of Urban Scenes Using Dense Depth Maps
  • 161
  • PDF
Towards a Global Optimal Multi-Layer Stixel Representation of Dense 3D Data
  • 94
  • PDF
Segmentation-based multi-class semantic object detection
  • 23
  • PDF
Segmentation and Recognition Using Structure from Motion Point Clouds
  • 688
  • Highly Influential
  • PDF
...
1
2
3
4
...