IEEE Transactions on Pattern Analysis and Machine Intelligence · 2009 · 103 citations · 38 references
ComputingAutonomous SystemsComputer VisionMachine VisionSensor FusionBayesian Sensor FusionDepth EstimationDepth PerceptionScene UnderstandingStereo VisionVisual SlamBelief PropagationDepth Map ReconstructionDepth-based LocalizationDynamic Scene ReconstructionDynamic Scene RepresentationRobustness To Dynamic ScenesTemporal CoherenceThree-dimensional Scene Reconstruction
Time-of-flight range sensors and passive stereo have complimentary characteristics in nature. To fuse them to get high accuracy depth maps varying over time, we extend traditional spatial MRFs to dynamic MRFs with temporal coherence. This new model allows both the spatial and the temporal relationship to be propagated in local neighbors. By efficiently finding a maximum of the posterior probability using Loopy Belief Propagation, we show that our approach leads to improved accuracy and robustness of depth estimates for dynamic scenes.
38
High-accuracy stereo depth maps using structured light
Daniel Scharstein, Richard Szeliski · 2003 · 1.5K citations
William T. Freeman · International Journal of Computer Vision · 2000 · 1.5K citations