Indoor frame recovering via line segments refinement and voting

Chu, Jun; Guo, Luanzheng; Wang, Lingfeng; Chen, Pan; Xiang, Shiming

doi:10.1109/icassp.2013.6638003

Cited by 6 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A preliminary version of this work appeared in [3]. This article extends the conference version of [3], with four kinds of frame models instead of the crab-like model, and a depth constraint as a complement, and discussions of applications and limitations.…”

Section: Introductionmentioning

confidence: 94%

See 1 more Smart Citation

Indoor Frame Recovery from Refined Line Segments

Guo,

Chu

2017

Preprint

Self Cite

View full text Add to dashboard Cite

An important yet challenging problem in understanding indoor scene is recovering indoor frame structure from a monocular image. It is more difficult when occlusions and illumination vary, and object boundaries are weak. To overcome these difficulties, a new approach based on line segment refinement with two constraints is proposed. First, the line segments are refined by four consecutive operations, i.e., reclassifying, connecting, fitting, and voting. Specifically, misclassified line segments are revised by the reclassifying operation; some short line segments are joined by the connecting operation; the undetected key line segments are recovered by the fitting operation with the help of the vanishing points; the line segments converging on the frame are selected by the voting operation. Second, we construct four frame models

show abstract

Section: Introductionmentioning

confidence: 94%

“…To describe the detail voting process, we define two functions: a normalization function ϕ(•) and a reverse normalization function η(•) 3 . We first initial the weight of each line segment in the groups of candidate box lines, the initial weight of candidate box line l i can be evaluated from two parts of length and angle:…”

Section: Votingmentioning

confidence: 99%

Indoor Frame Recovery from Refined Line Segments

Guo,

Chu

2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The line-networks comprised of line segments and connected nodes, contain important geometric information of an image, especially when the scene of the image is consisted of many man-made objects. Besides, line-networks can be used as low-level features to assist to solve problems such as stereo matching [2], [3], indoor scene layout recovering [4], road extraction [5], crack detection in materials, image compression, and so on.…”

Section: Introductionmentioning

confidence: 99%

NETLines: Recovering line-networks via gradient-based line segments refinement

Yao

et al. 2015

2015 IEEE International Conference on Information and Automation

View full text Add to dashboard Cite

In this paper, we propose a novel line segment detector, named as NETLines, which can produce a set of accurate line segments and a set of node-connected linenetworks formed by connection of the line segments and the image boundary. Based on the line segments generated by other line segment detectors (e.g., EDLines [1]) on an edge map, the proposed algorithm efficiently makes use of the gradient map of the original image instead of its edge map to extend and refine the line segments. The line-networks are constructed with the extended and refined line segments and a set of nodes generated by connecting of the line segments. Furthermore, the line segments and line-networks are optimally supplemented and refined by linking and merging the line segments. Experimental results on a set of natural images illustrate the proposed NETLines produces more accurate and complete line segments compared with state-of-the-art line segments detectors.

show abstract