Peter Forte

Combining Intelligent Agents and Animation

This paper reviews FreeWill and other AI architectures that have contributed to the ideas, which underlie it. “FreeWill” proposes and implements a cognitive architecture designed for easy creation of animated scenes with many autonomous agents interacting in various ways. The generation of animated human figures especially in crowd scenes has many applications in such domains as the special effects industry, computer games or for the simulation of the evacuation from crowded areas. Currently such scenes have to be created by human animators using dedicated software packages. This is both expensive and time-consuming. FreeWill combines and extends two existing architectures – Funge’s cognitive architecture and the recent SAC concept. Additionally it puts emphasis on strong design and provides easy co-operation of different software packages.

Construction of an FPA-type metric for early lifecycle estimation

Abstract The traditional function point approach has been well documented. Despite increasing popularity, investigations have shown a number of weaknesses. There is evidence that simple metrics may be as good as function points for early lifecycle estimates. This paper considers the use of a simplified approach to system size estimation that utilises function point elements. From this, the construction of a new model for producing function point estimates earlier in the development lifecycle is presented, together with results from application of the model to real project data.

Object-oriented recognition for automatic inspection

This paper describes work being carried out in the area of object recognition. The research is part of a project, at Kingston University (London), to automatically inspect surface-mounted assemblies. The system is designed to use some of the significant properties of the object-oriented paradigm to build a flexible architecture that can be applied to many inspection problems. The recognition system operates on a new information representation constructed from three inter-linked data structures. The application of the proposed object-oriented recognition framework, to inspect surface-mounted assemblies, will be described in this paper.

A Non-Linear Shape Abstraction Technique

This paper describes the implementation of a non-linear shape abstraction technique. The abstraction procedure systematically simplifies the shapes description using a group of predefined ‘rewrite rules’. This procedure operates on a new compact and efficient two dimensional shape representation.

The Application of AI Techniques for Automatic Generation of Crowd Scenes

Generation of animated human figures especially in crowd scenes has many applications in such domains as the special effects industry, computer games or for the simulation of the evacuation from crowded areas. Currently such scenes have to be created by human animators using dedicated software packages. This is both expensive and time-consuming. Our “FreeWill” prototype proposes and implements a cognitive architecture designed for easy creation of animated scenes with many autonomous agents interacting in various ways. Agents maintain an internal model of the world and fulfil their goals. The design allows for easy co-operation of different software packages (geometry engine, AI engine, sensing/actuating modules, simulation managing unit and a visualisation environment). The implementation language is Java and the graphics package is 3D Studio Max. The requirements capture process and design is being conducted and documented in the Unified Modelling Language (UML).

MDL based Structural Interpretation of Images under Partial Occlusion

In this paper an information theoretic approach is provided for resolving border ambiguity under partial occlusion. The proposed framework allows structural interpretation of images prior to the application of domain specific knowledge. The central idea behind MDL based figure-ground grouping is merging those place-token candidates whose composed description length (whole) is better than sum of their individual description lengths (parts). The computational theory is illustrated by application to blocks-world images.

Posing Structural Matching in Remote Sensing as an Optimisation Problem

The use of computer vision methodologies in remote sensing is likely to rise significantly in the near future with the launch of imaging sensors with very high spatial resolution: offering panchromatic resolutions of between 3 and 1 metres. This will begin to make it possible to use more complex shape models and context information in the analysis of man-made structures. This is likely to revolutionise topographic mapping, cartographic registration, and urban zone monitoring in particular. Extracting extended image features and their relationships from images will enable the application of structural matching techniques to three types of remote sensing registration problems: image-to-image registration, image-to-symbol cartographic registration, and multi-modal registration e.g. matching active SAR data to passively acquired chromatic data. In the rest of this paper we shall review the range of structural matching methods reported in the computer vision literature.

Transputer-based feature extraction and shape analysis

Abstract This paper describes computer vision software for a project, the aim of which is to develop a prototype of a fast, low-cost machine vision system for the inspection of surface mount electronic assemblies and solder joints. The system uses advanced edge detection and shape description software to analyse the board, taking data from a simple optical platform. This platform is used as opposed to more complex alternatives such as laser range-finding/profiling, structured light, thermal or X-ray techniques. Hence the sophistication of this system lies in the software and not in the data capture technology. Transputers are used to provide an economical means of attaining the necessary computational power for the image analysis. This leads to a low cost solution that would be attractive to surface mount manufacturers. This paper describes the software modules required to perform feature extraction and shape analysis for inspection and how the modules are parallelized to run on a transputer network.

Automatic inspection of electronic surface-mount assemblies

An approach to image analysis is described consisting of five stages: edge detection, thresholding, linking, shape description and shape abstraction. The approach is illustrated by applying the steps to the problem of automatic inspection.

Shape similarity and simplification

A method is proposed for migrating a planar shape through a scale space in which the shape is sampled on an irregular grid induced by curvature events along the shape contour. Because the grid is derived from the shape, the grid pattern itself changes in discrete steps as the shape is simplified. At each step the shape contour is reconstructed with an equal or fewer number of inflection points. An implementation is described based on a sampling grid generated by a Voronoi tessellation, and examples given of the resulting progressive simplification for two shapes. It is argued that the process simulates the simplification of a shape perceived by a human observer as the distance between observer and shape steadily decreases.