Visual interpretation of known objects in constrained scenes

1992 ◽  
Vol 337 (1281) ◽  
pp. 361-370 ◽  
Keyword(s):  
Object Recognition ◽  
Visual Perception ◽  
Machine Vision ◽  
Recent Work ◽  
Three Dimensional ◽  
Neural Mechanisms ◽  
Visual Interpretation ◽  
Natural Vision ◽  
Analogue Models ◽  
Dynamic Filters

Recent work on the visual interpretation of traffic scenes is described which relies heavily on a priori knowledge of the scene and position of the cam era, and expectations about the shapes of vehicles and their likely movements in the scene. Knowledge is represented in the computer as explicit three-dimensional geometrical models, dynamic filters, and descriptions of behaviour. Model-based vision, based on reasoning with analogue models, avoids many of the classical problems in visual perception: recognition is robust against changes in the image of shape, size, colour and illumination. The three-dimensional understanding of the scene which results also deals naturally with occlusion, and allows the behaviour of vehicles to be interpreted. The experiments with machine vision raise questions about the part played by perceptual context for object recognition in natural vision, and the neural mechanisms which might serve such a role.

Reflections on Photogrammetry

2018 ◽  
pp. 34-41
Author(s):  
Alexander W. Schindler
Keyword(s):  
Object Recognition ◽  
Machine Vision ◽  
Three Dimensional ◽  
Standard Technique ◽  
Ground Truth ◽  
Reference Points ◽  
Two Dimensional ◽  
Three Dimensional Model ◽  
Technological Field ◽  
Image Capturing

This article presents an overview of the history, principles, and current developments in the media technological field of photogrammetry. By chronicling the isomorphic shift taking place in image capturing, we seek to show that photogrammetry has led the way forward in seeing technical images not only as two dimensional projections, but as three-dimensional model-based images. In the mid-nineteenth century, photogrammetry was first used for the documentation of architectural objects and it later became a standard technique in aerial photography. Although its fields of application have become more extensive, photogrammetry’s basic principle hasn’t fundamentally changed: it is still defined as the three- dimensional geometric reconstruction of two-dimensional photographs through the measuring of reference points. With digital technological standards and advances in camera technology, photogrammetric imaging nowadays is intensively used for object recognition in machine vision and robotics. Beside this, photogrammetry is also opening new possibilities for documentation in the fields of investigative arts, this being explored with a discussion on the “Ground Truth” project from Forensic Architecture. Keywords: investigative art, machine vision, object recognition, photogrammetry, photography

Art and Ambiguity

2018 ◽  
Author(s):  
John O’Dea
Keyword(s):  
Perceptual Experience ◽  
Three Dimensional ◽  
Empirical Work ◽  
Visual Interpretation ◽  
Perceptual Constancy ◽  
Multistable Perception ◽  
State Of Affairs

This chapter defends a solution to the problem of variable appearances that co-occur with perceptual constancy. In conditions which are non-ideal, yet within the range of perceptual constancy, we see things veridically despite a puzzling “appearance” which is suggestive of a non-veridical state of affairs. For example, a tilted coin is often taken to have an “elliptical appearance”. This chapter defends Gestalt-shift approach, according to which these appearances are in fact illusory, but not part of normal perceptual experience. The experience of ellipticality when viewing a tilted coin, it is argued, arises from something like a brief and unstable Gestalt shift to a different visual interpretation of the scene, of the kind that E. H. Gombrich argued artists invoke when painting a three-dimensional scene on a flat canvas. Recent empirical work on multistable perception is used to show how this might work.

Recent Developments in the Evolution of Morphologies and Controllers for Physically Simulated Creatures

2001 ◽  
Vol 7 (1) ◽  
pp. 77-87 ◽  
Author(s):  
Tim Taylor ◽  
Colm Massey
Keyword(s):  
Recent Work ◽  
Original Work ◽  
Three Dimensional ◽  
Parallel Computer ◽  
Connection Machine ◽  
Recent Developments ◽  
Body Shapes

Karl Sims' work [25, 26] on evolving body shapes and controllers for three-dimensional, physically simulated creatures generated wide interest on its publication in 1994. The purpose of this article is threefold: (a) to highlight a spate of recent work by a number of researchers in replicating, and in some cases extending, Sims' results using standard PCs (Sims' original work was done on a Connection Machine CM-5 parallel computer). In particular, a re-implementation of Sims' work by the authors will be described and discussed; (b) to illustrate how off-the-shelf physics engines can be used in this sort of work, and also to highlight some deficiencies of these engines and pitfalls when using them; and (c) to indicate how these recent studies stand in respect to Sims' original work.

Sign in / Sign up

Export Citation Format

Share Document