On-line semantic perception using uncertainty

Visual perception capabilities are still highly unreliable in unconstrained settings, and solutions might not be accurate in all regions of an image. Awareness of the uncertainty of perception is a fundamental requirement for proper high level decision making in a robotic system. Yet, the uncertainty measure is often sacrificed to account for dependencies between object/region classifiers. This is the case of Conditional Random Fields (CRFs), the success of which stems from their ability to infer the most likely world configuration, but they do not directly allow to estimate the uncertainty of the solution. In this paper, we consider the setting of assigning semantic labels to the pixels of an image sequence. Instead of using a CRF, we employ a Perturb-and-MAP Random Field, a recently introduced probabilistic model that allows performing fast approximate sampling from its probability density function. This allows to effectively compute the uncertainty of the solution, indicating the reliability of the most likely labeling in each region of the image. We report results on the CamVid dataset, a standard benchmark for semantic labeling of urban image sequences. In our experiments, we show the benefits of exploiting the uncertainty by putting more computational effort on the regions of the image that are less reliable, and use more efficient techniques for other regions, showing little decrease of performance.

Authors

• Roderick de Nijs
• Sebastian Ramos
• Gemma Roig
• Xavier Boix
• Luc Van Gool
• Kolja Kühnlenz

Keywords

• Labeling
• Uncertainty
• Semantics
• Random variables
• Computational modeling
• Robots
• Probabilistic logic
• Probability Density
• Probabilistic Model
• Probability Density Function
• Random Fields
• Image Regions
• Computational Effort
• Semantic Labels
• Conditional Random Field
• Support Vector Machine
• Markov Chain Monte Carlo
• Energy Function
• Color Difference
• Semantic Segmentation
• Accurate Characterization
• Online System
• Partition Function
• Dense Grid
• Video Segments
• Fast Feature
• Drawing Samples
• Global Accuracy
• Pooling Regions
• Patch Extraction
• Belief Propagation
• Scene Regions
• Temporal Consistency
• Set Of Perturbations
• Percentage Of Nodes