Simultaneous image segmentation and 3D plane fitting for RGB-D sensors &amp;#x2014; An iterative framework

Guan, Li; Yu, Tao; Tu, Peter; Lim, Ser-Nam

doi:10.1109/cvprw.2012.6238914

Cited by 9 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Salas-Moreno et al 5 presented a similar approach to detect planes using connected component labeling. 18 Guan et al 19 treat the range image as a Markov random field and solve the association problem using graph-based global energy minimization, which encapsulates both appearance cues from the RGB (color) channels and shape cues from the D (depth) channel. This approach suggests significant segmentation quality at genuine plane edges and plane intersections and also automatically fills in missing depth information.…”

Section: Related Workmentioning

confidence: 99%

Fast plane segmentation with line primitives for RGB-D sensor

Zhang

Chen

Liu

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This article presents a fast and robust plane segmentation approach for RGB-D type sensor, which detects plane candidates by line segments extracted from 2-D scanline projected from row or column points. It neither requires high computation to calculate local normals for the entire point cloud as most of approaches do nor randomly chooses plane candidates such as RANSAC-like approaches. First, a line extraction algorithm is utilized to extract line segments. Second, the plane candidates are detected by estimating local normal of points lying on line segments. Finally, the plane having most inlier is recursively extracted from the plane candidates as the result plane. Experiments were conducted with different data sets and the segmentation performances were evaluated quantitatively and qualitatively. We demonstrated the efficiency and robustness of our proposed approach, especially in the none plane scenario, the approach needs little computational cost.

show abstract

Section: Related Workmentioning

confidence: 99%

Fast plane segmentation with line primitives for RGB-D sensor

Zhang

Chen

Liu

2016

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Silberman et al [17] propose to use a Conditional Random Field (CRF) based model to evaluate a range of different representations for depth information and a novel prior on 3D location. In Guan et al [10], the image is segmented in an initial number of planes, followed by a pixel-to-plane assignment. Plane equations are iteratively refined.…”

Section: Related Workmentioning

confidence: 99%

Plane Extraction for Indoor Place Recognition

Potena

Pretto

Bloisi

et al. 2015

Advanced Concepts for Intelligent Vision Systems

View full text Add to dashboard Cite

In this paper, we present an image based plane extraction method well suited for real-time operations. Our approach exploits the assumption that the surrounding scene is mainly composed by planes disposed in known directions. Planes are detected from a single image exploiting a voting scheme that takes into account the vanishing lines. Then, candidate planes are validated and merged using a region growing based approach to detect in real-time planes inside an unknown indoor environment. Using the related plane homographies is possible to remove the perspective distortion, enabling standard place recognition algorithms to work in an invariant point of view setup. Quantitative Experiments performed with real world images show the effectiveness of our approach compared with a very popular method.

show abstract

“…The proposed method's motivation is based on the fact that the 3D geometric segment structure from a real scene can be represented as piecewise LSMs [12], [13]. Based on the motivation, a depth image with linear surfaces is first modeled, and the depth value of the hole is estimated by selecting one of the LSMs.…”

Section: Introductionmentioning

confidence: 99%

A novel depth image enhancement method based on the linear surface model

Kang

Kim

et al. 2014

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

In three-dimensional (3D) video applications, structured-light RGB-D cameras are commonly used to capture depth images that convey the per-pixel depth information in a scene. However, these cameras often produce regions with missing pixels (MPs). These regions, referred to as holes, will not contain no any depth information for the captured depth image. In this paper, a novel depth image enhancement method that accurately estimates depth values of MPs is presented. In the proposed method, the neighboring region outside the hole is first segmented into superpixels using simple linear iterative clustering. Subsequently, the depth value trend of each superpixel is modeled as a linear surface. Finally, one of the linear surfaces is selected using a proposed metric, to estimate the depth value of a particular MP in the hole. Experimental results demonstrate that the proposed method provides superior performance, especially around the object boundary, compared with other state-of-theart depth image enhancement methods 1 .Index Terms -Depth image enhancement, hole filling, least squares method, linear surface model, piecewise linear approximation, structured-light RGB-D camera.

show abstract

Simultaneous image segmentation and 3D plane fitting for RGB-D sensors — An iterative framework

Cited by 9 publications

References 37 publications

Fast plane segmentation with line primitives for RGB-D sensor

Fast plane segmentation with line primitives for RGB-D sensor

Plane Extraction for Indoor Place Recognition

A novel depth image enhancement method based on the linear surface model

Contact Info

Product

Resources

About