Depth-wise layering of 3d images using dense depth maps: a threshold based approach

TL;DR

This paper introduces a threshold-based depth-wise layering method for segmenting static scene images into multiple layers using dense depth maps, offering a novel approach to depth-wise segmentation in computer vision.

Contribution

It presents a new depth-wise layering technique that segments images into layers using a thresholding approach on dense depth maps, which is different from traditional surface-wise segmentation methods.

Findings

Effective segmentation of static scenes into layers

Promising results demonstrated on multiple images

Independent identification of objects and layers

Abstract

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.