New 3d segmentation approach for reverse engineering selective sampling acquisition

Courtial, Azelle; Vezzetti, Enrico

doi:10.1007/s00170-006-0772-3

Cited by 10 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method can be combined with results from studies of the tool engagement angle to realize greater improvements in the endmilling process. The methods described in this study also have applications in the reverse engineering of complex surfaces, which focus on tracing the geometrical features of a physical model [18,19].…”

Section: Endmilling Surface Generationmentioning

confidence: 99%

See 1 more Smart Citation

Improving endmilling surface finish by workpiece rotation and adaptive toolpath spacing

Vijayaraghavan

Hoover

Hartnett

et al. 2009

International Journal of Machine Tools and Manufacture

View full text Add to dashboard Cite

a b s t r a c tFree-form surfaces are being used in a growing number of engineering applications, especially in injection molding of consumer products. Decreasing the manufacturing cost and time of these molds will improve the efficiency of manufacturing injection molded consumer products. This paper is motivated by the need for simple strategies to improve the quality of and decrease the time required to machine free-form surfaces. We present two methods to improve the surface finish of parts finished with ball-nose endmilling. In the first method the surface finish is improved by finding an optimal orientation angle for the workpiece relative to the machining axis. In the second method finish is improved by adaptively varying the step-size when using raster toolpaths. The adaptive variation is controlled by a user-defined finish improvement factor, where the spacing density is increased only if the improvement in surface finish is greater than the finish improvement factor. These methods are implemented using an analytical model of the workpiece surface finish based on the mean scallop height of the machined surface. Results from the analytical model are verified with machining experiments, and we show that the adaptive spacing strategy can improve the surface quality by more than 50% with a small increase in the toolpath length. To achieve a similar improvement in surface quality by uniformly decreasing the path spacing results in a much larger increase in the toolpath length. The strategies discussed in this paper allow process planners intuitive control over the toolpath layout and spacing and improve the efficiency of machining high quality parts.

show abstract

Section: Endmilling Surface Generationmentioning

confidence: 99%

“…The method can be extended to adaptively change the machining parameters such as RPM and feed in real-time based on the local workpiece features. Techniques used in the reverse engineering of complex surfaces can also be applied in improving the accuracy of the analytical model with respect to experimental results [18,19].…”

Section: Article In Pressmentioning

confidence: 99%

Improving endmilling surface finish by workpiece rotation and adaptive toolpath spacing

Vijayaraghavan

Hoover

Hartnett

et al. 2009

International Journal of Machine Tools and Manufacture

View full text Add to dashboard Cite

show abstract

“…For instance, splitting an image or a 3D object in smaller parts is very useful to perform high-level recognition (Kokkinos and Maragos, 2009;Ferrari et al, 2006), reverse engineering (Courtial and Vezzetti, 2008;Kim et al, 2002), parts retrieval (Antini et al, 2005) and even tracking (Colombari et al, 2007). Of course, the expected outcome of a segmentation procedure is different depending on the intended use of the resulting parts.…”

Section: Introductionmentioning

confidence: 99%

A graph-based technique for semi-supervised segmentation of 3D surfaces

Bergamasco

Albarelli

Torsello

2012

Pattern Recognition Letters

View full text Add to dashboard Cite

a b s t r a c tA wide range of cheap and simple to use 3D scanning devices has recently been introduced in the market. These tools are no longer addressed to research labs and highly skilled professionals, but rather, they are mostly designed to allow inexperienced users to acquire surfaces and whole objects easily and independently. In this scenario, the demand for automatic or semi-automatic algorithms for 3D data processing is increasing. In this paper we address the task of segmenting the acquired surfaces into perceptually relevant parts. Such a problem is well known to be ill-defined both for 2D images and 3D objects, as even with a perfect understanding of the scene, many different and incompatible semantic or syntactic segmentations can exist together. For this reason recent years have seen a great research effort into semi-supervised approaches, that can make use of small bits of information provided by the user to attain better accuracy. We propose a semi-supervised procedure that exploits an initial set of seeds selected by the user. In our framework segmentation happens by propagating part labels over a weighted graph representation of the surface directly derived from its triangulated mesh. The assignment of each element is driven by a greedy approach that accounts for the curvature between adjacent triangles. The proposed technique does not require to perform edge detection or to fit parametrized surfaces and its implementation is very straightforward. Still, despite its simplicity, tests made on a standard database of scanned 3D objects show its effectiveness even with moderate user supervision.

show abstract

“…For instance, splitting an image or a 3D object in smaller parts is very useful to perform high-level recognition [1,2], reverse engineering [3,4] and even tracking [5]. Of course, the expected outcome of a segmentation procedure is different depending on the intended use of the resulting parts.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised Segmentation of 3D Surfaces Using a Weighted Graph Representation

Bergamasco

Albarelli

Torsello

2011

Graph-Based Representations in Pattern Recognition

View full text Add to dashboard Cite

Abstract. A wide range of cheap and simple to use 3D scanning devices has recently been introduced in the market. These tools are no longer addressed to research labs and highly skilled professionals. By converse, they are mostly designed to allow inexperienced users to easily and independently acquire surfaces and whole objects. In this scenario, the demand for automatic or semi-automatic algorithms for 3D data processing is increasing. Specifically, in this paper we concentrate on the segmentation task applied to the acquired surfaces. Such a problem is well known to be ill-defined both for 2D images and 3D objects. In fact, even with a perfect understanding of the scene, many different and incompatible semantic or syntactic segmentations can exist together. For this reasons, we refrain from any attempt to offer an automatic solution. Instead we introduce a semi-supervised procedure that exploits an initial set of seeds selected by the user. In our framework segmentation happens by iteratively visiting a weighted graph representation of the surface starting from the supplied seeds. The assignment of each element is driven by a greedy approach that accounts for the curvature between adjacent triangles. The proposed technique does not require to perform edge detection or to fit parametrized surfaces and its implementation is very straightforward. Still, despite its simplicity, tests made on scanned 3D objects show its effectiveness and easiness of use.

show abstract

New 3d segmentation approach for reverse engineering selective sampling acquisition

Cited by 10 publications

References 11 publications

Improving endmilling surface finish by workpiece rotation and adaptive toolpath spacing

Improving endmilling surface finish by workpiece rotation and adaptive toolpath spacing

A graph-based technique for semi-supervised segmentation of 3D surfaces

Semi-supervised Segmentation of 3D Surfaces Using a Weighted Graph Representation

Contact Info

Product

Resources

About