Hod Lipson

Identification of faces in a 2D line drawing projection of a wireframe object

An important key to reconstructing a three-dimensional object depicted by a two-dimensional line drawing projection is face identification. Identification of edge circuits in a 2D projection corresponding to actual faces of a 3D object becomes complex when the projected object is in wireframe representation. This representation is commonly encountered in drawings made during the conceptual design stage of mechanical parts. When nonmanifold objects are considered, the situation becomes even more complex. This paper discusses the principles underlying face identification and presents an algorithm capable of performing this identification. Face-edge-vertex relationships applicable to nonmanifold objects are also proposed. Examples from a working implementation are given.

Classification of sketch strokes and corner detection using conic sections and adaptive clustering

This paper presents a method for classifying pen strokes in an on-line sketching system. The method, based on linear least squares fitting to a conic section equation, proposes using the conic equations natural classification property to help classify sketch strokes and identify lines, elliptic arcs, and corners composed of two lines with an optional fillet. The hyperbola form of the conic equation is used for corner detection. The proposed method has proven to be fast, suitable for real-time classification, and capable of tolerating noisy input, including cusps and spikes. The classification is obtained in o(n) time in a single path, where n is the number of sampled points. In addition, an improved adaptive method for clustering disconnected endpoints is proposed. The notion of in-context analysis is discussed, and examples from a working implementation are given.

Conceptual design and analysis by sketching

The ability of a CAD system to perceive a three-dimensional model depicted in a single freehand sketch presents the practical possibility of bringing numerous established analysis tools into the early stages of design to institute conceptual analysis. In this article we hypothesize that the key to enabling systems to reason and communicate about conceptual design is the language of sketching. We explore this approach, outline the basic algorithms required, and provide several examples of an implemented system.

A New Interface for Conceptual Design Based on Object Reconstruction from a Single Freehand Sketch

Abstract A new system has been developed for improving user interaction with CAD systems, particularly in the conceptual design stage. The system is based on interactive, part-by-part formation of a geometrical model using freehand sketching. A single 2D inaccurate projection is entered in the form of a line drawing. The system analyzes and interprets the input and then reconstructs a 3D model of the object most likely to be represented by the sketch. This 3D model can be further manipulated or modified, and more parts can be sketched. This approach provides a fluent and intuitive tool for conceptual design. In the paper, the proposed system is presented and the basic ideas are discussed and exemplified.

3D conceptual design of sheet metal products by sketching

Abstract Design of sheet metal products can be a complex and elaborate process. However, many important aspects of the manufacturing characteristics of a product are already determined at the early stages of the design. This paper reports on a system for conceptual design of sheet metal products by sketching, based on principles of early incorporation of CAD, imprecise analysis, and natural, in-context interaction. Using this approach, various preliminary aspects of a product, such as manufacturability, optimal flat pattern, weight and cost can be estimated automatically based on only a rough freehand sketch of a product, without requiring accurate details. This approach permits designers to explore new concepts more freely and to make a sounder decision when selecting a particular concept for detailed design. The paper describes the concept of the proposed methodology and its underlying algorithms for efficient flat pattern determination based on fuzzy AI techniques. Examples from a working implementation are shown.

Clustering Irregular Shapes Using High-Order Neurons

This article introduces a method for clustering irregularly shaped data arrangements using high-order neurons. Complex analytical shapes are modeled by replacing the classic synaptic weight of the neuron by high-order tensors in homogeneous coordinates. In the first- and second-order cases, this neuron corresponds to a classic neuron and to an ellipsoidal-metric neuron. We show how high-order shapes can be formulated to follow the maximum-correlation activation principle and permit simple local Hebbian learning. We also demonstrate decomposition of spatial arrangements of data clusters, including very close and partially overlapping clusters, which are difficult to distinguish using classic neurons. Superior results are obtained for the Iris data.

Engineering Environments in the Information Age: Research Challenges and Opportunities

Abstract This paper examines changes to the contemporary product engineering cycle resulting from the Information Age and identifies information-related obstacles that correspond to the human dimension of information overload in engineering. These obstacles may explain why increases in productivity have been disappointing and why information technology has not been able to satisfy the increasing demands placed on contemporary engineers. Three productivity impeding categories are discussed: (a) detail overload, (b) constraint overload, and (c) versatility overload. The authors suggest how new emerging paradigms and technologies can be harnessed to alleviate the identified difficulties. Three directions for improvement are discussed: (a) bringing computer tools into the engineering process earlier, permitting more extensive exploration and informed selection of alternatives, (b) improving human-computer interfaces towards in-context natural interaction, making information exchange more fluent and fast, and (c) transforming computers from passive to active self-initiated engineering aids that can suggest alternatives and convey relevant information. The paper discusses applications to areas such as design, manufacturing, simulation, quality assurance, and maintenance.

Optimization-based reconstruction of a 3D object from a single freehand line drawing

This paper describes an optimization-based algorithm for reconstructing a 3D model from a single, inaccurate, 2D edge-vertex graph. The graph, which serves as input for the reconstruction process, is obtained from an inaccurate free-hand sketch of a 3D wireframe object. Compared with traditional reconstruction methods based on line labelling, the proposed approach is more tolerant of faults in handling both inaccurate vertex positioning and sketches with missing entities. Furthermore, the proposed reconstruction method supports a wide scope of general (manifold and non-manifold) objects containing flat and cylindrical faces. Sketches of wireframe models usually include enough information to reconstruct the complete body. The optimization algorithm is discussed, and examples from a working implementation are given.

An interface for 3D conceptual design based on freehand sketching

This research proposes and implements a new user interface, based on freehand sketching, for three-dimensional conceptual design. There are several difficulties in implementing this kind of interface. The primary difficulty is that the reconstruction is mathematically indeterminate because the two-dimensional sketch lacks three-dimensional depth information. Inaccuracies inherent in the freehand sketch intensify the difficulty. The proposed reconstruction algorithm operates in several stages. First, the raw sketch is analyzed, and basic geometrical entities (lines, elliptic arcs and corners) are identified and smoothed. These entities are then linked to form an edge-vertex graph representing the two-dimensional topology of the object’s projection. The three-dimensional object is then reconstructed using implicit spatial cues in the sketch plane. These cues originate from three main sources: (a) geometrical regularities, (h) sketch topology, and (c) statistical distribution of entities in the sketch plane. This paper proposes a sketch-based interface, discusses the underlying algorithms and provides examples from a working implementation.

Automatic Reasoning for Design under Geometrical Constraints

Abstract Parametric design is very stable but requires a predefined dimensioning and ordering scheme, thus limiting flexibility and precluding sketch input. Variational geometry design, while general and flexible, necessitates intensive use of numerical solvers to solve many simultaneous nonlinear equations. Frequently the solvers cannot solve these equations. A new system, based on an original theory for automatic constraint analysis, has been developed for solving sets of two-dimensional geometric constraints in product design. The proposed system offers the flexibility of variational based design along with the stability of parametric design. The solution strategy is based upon breaking down the problem into a sequence of construction steps. When no sequential construction is found, auxiliary geometrical constructions are automatically generated based on rules for relocating constraints. Thus, an apparently simultaneous constraint set is converted into a set that can be constructed sequentially by decomposing strongly connected components of the original constraint graph. This new approach has been implemented in a system for designing sheet metal parts.