Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Information Theory, Inference & Learning Algorithms
Information Theory, Inference & Learning Algorithms
Efficient Dense Scene Flow from Sparse or Dense Stereo Data
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Applying Recursive EM to Scene Segmentation
Proceedings of the 31st DAGM Symposium on Pattern Recognition
Detection and Segmentation of Independently Moving Objects from Dense Scene Flow
EMMCVPR '09 Proceedings of the 7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
Colour, texture, and motion in level set based segmentation and tracking
Image and Vision Computing
Estimating the driving state of oncoming vehicles from a moving platform using stereo vision
IEEE Transactions on Intelligent Transportation Systems
Dense, robust, and accurate motion field estimation from stereo image sequences in real-time
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
A comparative study of energy minimization methods for markov random fields
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Mid-level segmentation and segment tracking for long-range stereo analysis
PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
| Hi-index | 0.00 |
A multi-class traffic scene segmentation approach based on scene flow data is presented. Opposed to many other approaches using color or texture features, our approach is purely based on dense depth and 3D motion information. Using prior knowledge on tracked objects in the scene and the pixel-wise uncertainties of the scene flow data, each pixel is assigned to either a particular moving object class (tracked/unknown object), the ground surface, or static background. The global topological order of classes, such as objects are above ground, is locally integrated into a conditional random field by an ordering constraint. The proposed method yields very accurate segmentation results on challenging real world scenes, which we made publicly available for comparison.