arXiv (Cornell University) · 2017 · 11 citations · 1 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningDepth EstimationInstance SegmentationObject DetectionScene UnderstandingSemantic Segmentation3D Semantic SegmentationConditional Random FieldsConvolutional Neural Network SegmentationConvolutional Neural NetworksFully Convolutional NetworksSegmentation Performance AnalysisSemantic Scene Parsing
To improve segmentation performance, a novel neural network architecture (termed DFCN-DCRF) is proposed, which combines an RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditional random field (DCRF). First, a DFCN architecture which fuses depth information into the early layers and applies dilated convolution for later contextual reasoning is designed. Then, a depth-sensitive fully-connected conditional random field (DCRF) is proposed and combined with the previous DFCN to refine the preliminary result. Comparative experiments show that the proposed DFCN-DCRF has the best performance compared with most state-of-the-art methods.
1