Segmenting reliefs on triangle meshes

Liu, Shenglan; Martin, Ralph R.; Langbein, Frank C.; Rosin, Paul L.

doi:10.1145/1128888.1128890

Cited by 20 publications

(26 citation statements)

References 18 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this approach, the user simply draws an initial contour for the snake, which again may be far from the final boundary. On the smoothed mesh, we apply our previous approach, for relief segmentation on a surface with a smooth background, to move the initial contour to the relief boundary [30]. In the coarse evolution phase, we adopt the same energy terms as before such as internal energy, feature energy and deflation energy.…”

Section: Overview Of the Smoothing Approachmentioning

confidence: 99%

See 1 more Smart Citation

Segmenting Geometric Reliefs from Textured Background Surfaces

Liu

Martin

Langbein

et al. 2007

Computer-Aided Design and Applications

Self Cite

View full text Add to dashboard Cite

Fig. 1: A pen container showing a relief on a textured background and a corresponding segmentation.ABSTRACT Segmentation of geometric reliefs from a textured background has various applications in reverse engineering. We consider two approaches to solve this problem. The first classifies parts of a surface mesh as relief or background, and then uses a snake which moves inwards towards the desired relief boundary, which is coarsely located using an energy based on the classification. The second approach initially smoothes the surface to eliminate the background texture, and locates the snake at the relief boundary using an energy based on the step between the background and the relief.Both snakes start at simple user-drawn contours, and are driven towards the relief boundaries by the snake energy functional. In both cases, the snake has different evolution phases with different energy terms, to initially rapidly drive the snake towards the relief boundary, and to later accurately match it.To describe geometric textures, we analyze surface differential properties, and integral and statistical quantities based upon them, computed at multiple scales taken over local neighborhoods, following similar ideas from image texture processing. For classification, we use a support vector machine together with sequential forward floating search for feature selection. A straightforward Laplacian method is used for smoothing.We use example scanned models to demonstrate that both approaches are useful, but are suitable for different types of model.

show abstract

Section: Overview Of the Smoothing Approachmentioning

confidence: 99%

“…We use a somewhat different approach to the snake used on a smooth background in our earlier work [30]. There, snake evolution has three basic phases, each with a particular goal: coarse evolution, contour refinement and final stabilization.…”

Section: Snake-based Segmentationmentioning

confidence: 99%

Segmenting Geometric Reliefs from Textured Background Surfaces

Liu

Martin

Langbein

et al. 2007

Computer-Aided Design and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…Third, the extra forces have to be calculated upon mesh features, instead of intensity image features. And finally, the snake must be restricted to lie on the mesh at the energy function minimum (Liu et al, 2006).…”

Section: Th International Symposium On Automation and Robotics In Conmentioning

confidence: 99%

A 3D Snake Approach for Extracting Plans of Heritage Buildings

Llamas¹,

Melero²,

Zalama³

et al. 2010

Proceedings -- The 27th International Symposium on Automation and Robotics in Construction

View full text Add to dashboard Cite

A comprehensive documentation of construction surveying is always desirable and, in the case of cultural heritage, imperative. Detailed layouts of heritage constructions help the understanding of the historical development of the building, however, drawing these plans is, usually, a manual process. In this paper, we present a new approach for obtaining accurate plans that include stone by stone drawings using 3D models. The proposed method overcomes the manual detection and drawing of features and individual stones. The approach works on 3D snakes (energy-minimizing active contour models) and on the detection of feature lines upon a surface curvature analysis. Our method can be applied to 3D meshes obtained with different techniques, but we have focused on 3D laser scanner techniques, which provide large amount of data quickly and accurately. Experimental results obtained on a romanesque church in Spain, are also given to illustrate the usefulness of the approach.

show abstract

“…More complex, in terms of processing, are reliefs lying on a textured background. We have already addressed the segmentation problem-separating the relief from the underlying background-for such cases in [1] and [2].…”

Section: Introductionmentioning

confidence: 99%

“…The relief's outer boundaries can be detected using our previous segmentation methods: see [1] for the smooth background case, and [2] for textured backgrounds. These methods separate reliefs from their underlying surface using an active contour (or snake) driven by energy terms based on two significant relief characteristics, the raised step at the relief boundary, or the difference in surface properties between the relief and the background surface.…”

Section: Introductionmentioning

confidence: 99%

Segmenting Periodic Reliefs on Triangle Meshes

Liu

Martin

Langbein

et al.

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Decorative reliefs are widely used for e.g. packaging and porcelain design. In periodic reliefs, the relief repeats a pattern, for example all the way around an underlying surface of revolution. Reverseengineering of existing reliefs allows them to be re-applied to different base surfaces; we show here how to segment a single repeat unit of a periodic relief starting from a scanned triangle mesh.We first briefly review how we segment the relief from the background surface using our previous work. The rest of the paper then concentrates on how we extract a single repeat unit from the relief. To do so, the user provides two points on one relief boundary which are in approximate correspondence on consecutive repeats of the relief. We first refine the relative locations of these points, and then determine a third corresponding point using relief boundary information. These are used to determine three initial cutting planes across the relief. Then surface registration strategies are utilised to refine the correspondence between adjacent repeat units. Finally, we refine the exact locations of the cutting planes by considering only surface information close to the cutting planes. This allows a repeat unit of the periodic relief to be extracted.We demonstrate that our algorithm is successful and practical, using various real scanned models: user input can be quite imprecise, and we can cope with hand-made reliefs in which the pattern units are only approximately copies of each other.

show abstract

Segmenting reliefs on triangle meshes

Cited by 20 publications

References 18 publications

Segmenting Geometric Reliefs from Textured Background Surfaces

Segmenting Geometric Reliefs from Textured Background Surfaces

A 3D Snake Approach for Extracting Plans of Heritage Buildings

Segmenting Periodic Reliefs on Triangle Meshes

Contact Info

Product

Resources

About