Depth-wise layering of 3d images using dense depth maps: a threshold based approach
This addresses a specific segmentation problem in computer vision for static scenes, but it appears incremental as it builds on existing depth map techniques.
The paper tackles the problem of depth-wise layering for 3D images by proposing a threshold-based approach using dense depth maps to segment scenes into multiple layers, with experiments showing promising results.
Image segmentation has long been a basic problem in computer vision. Depth-wise Layering is a kind of segmentation that slices an image in a depth-wise sequence unlike the conventional image segmentation problems dealing with surface-wise decomposition. The proposed Depth-wise Layering technique uses a single depth image of a static scene to slice it into multiple layers. The technique employs a thresholding approach to segment rows of the dense depth map into smaller partitions called Line-Segments in this paper. Then, it uses the line-segment labelling method to identify number of objects and layers of the scene independently. The final stage is to link objects of the scene to their respective object-layers. We evaluate the efficiency of the proposed technique by applying that on many images along with their dense depth maps. The experiments have shown promising results of layering.