Our goal is to automatically generate CAD 3D models from 2D sketches as part of a design chain where models should be procedural, containing features arranged in a model tree and linked to suitable datums. Current procedural models capture much about the design intent and are easy to edit, but must be created from scratch during the detailed design state—given conceptual sketches as used by designers in the early part of the design process, current sketch-based modeling approaches only output explicit models. Thus, we describe an approach to extract high-level information directly from 2D engineering wireframe sketches and use it to complete a CSG feature tree, which serves as a model tree for a procedural 3D CAD model. Our method extracts procedural model information directly from 2D sketches in the form of a set of features, plus a set of datums and relationships between these features. We detect and analyze features of 2D sketches in isolation, and define the CSG feature tree by the parent–child relationships between features, and combine this information to obtain a complete and consistent CSG feature tree that can be transferred to a 3D modeler, which reconstructs the model. This paper focuses on how to extract the feature datums and the extrusion operation from an input 2D sketch.

In this article, visual perception principles were used to build an artificial perception model aimed at developing an algorithm for detecting junctions in line drawings of polyhedral objects that are vectorized from hand-drawn sketches. The detection is performed in two dimensions (2D), before any 3D model is available and minimal information about the shape depicted by the sketch is used. The goal of this approach is to not only detect junctions in careful sketches created by skilled engineers and designers but also detect junctions when skilled people draw casually to quickly convey rough ideas. Current approaches for extracting junctions from digital images are mostly incomplete, as they simply merge endpoints that are near each other, thus ignoring the fact that different vertices may be represented by different (but close) junctions and that the endpoints of lines that depict edges that share a common vertex may not necessarily be close to each other, particularly in quickly sketched drawings. We describe and validate a new algorithm that uses these perceptual findings to merge tips of line segments into 2D junctions that are assumed to depict 3D vertices.

I comment on a paper describing a method for deducing the hidden topology of an object portrayed in a 2D natural line drawing. The principal problem with this paper is that it cannot be considered an advance on (or even an equal of) the state of the art as the approach it describes makes the same limiting assumptions as approaches proposed 10 years ago. There are also important omissions in the review of related work.

I comment on a paper describing a method for inflating a 2D wireframe topological representation of an object to 3D. There are several problems with this paper and the method it describes. An oversimplified problem statement and concentration on mathematical ingenuity rather than comprehension lead the authors to develop a method which is not well-suited to the problem. Failure to take proper account of previous work leads them to compare their method, not with the true state of the art, but with older, less successful approaches. Finally, they omit entirely any mention of, let alone a proposed solution to, the most intractable problem in the area, that of finding resolution sequences.

As part of the goal of automatic creation of B-rep models of engineering objects from freehand sketches, we seek to take a single line drawing (with hidden lines removed), and from it deduce an initial 3D geometric realisation of the visible part of the drawn object. Junction and line labels, and provisional depth coordinates, are key parts of this frontal geometry. Many methods for producing frontal geometry only work correctly for drawings of trihedral objects. However, nontrihedral k-vertices commonly occur in engineering objects. We analyse the performance of a line-labelling method applied to k-vertices, and show why methods ignoring geometric considerations are inadequate. We give a new approach which produces both junction labels and provisional depth coordinates without any prior knowledge. Our results show that even a naive implementation outperforms previous methods.

This paper describes a system which converts a two-dimensional sketch with hidden lines removed of a single polyhedral object into a boundary representation solid model. The system improves on a previous system by Grimstead (1997) by analysing the sketch for symmetry elements and regularities. It uses the results of this analysis to produce a more plausible topological completion of the hidden parts of the object, and to enforce exact constraints on the geometry of the boundary-representation model.

Regulatory bodies require evidence that software controlling potentially hazardous devices is developed to good manufacturing practices. Effective techniques used in other industries assume long timescales and high staffing levels and can be unsuitable for use without adaptation in developing electronic healthcare devices. This paper discusses a set of techniques used in practice to develop software for a particular innovative medical product, an endoscopic camera manipulator. These techniques include identification of potential hazards and tracing their mitigating factors through the project lifecycle.