Obtaining exact depth from binocular disparities is hard if camera calibration is needed. We will show that qualitative information can be obtained from stereo disparities with little computation, and without prior knowledge (or computation) of camera parameters. First, we derive two expressions that order all matched points in the images by depth in two distinct ways from image coordinates only. Using one for tilt estimation and point separation (in depth) demonstrates some anomalies observed in psychophysical experiments, most notably the "induced size effect". We apply the same approach to detect qualitative changes in the curvature of a contour on the surface of an object, with either x- or y-coordinate fixed. Second, we develop an algorithm to compute axes of zero-curvature from disparities alone. The algorithm is shown to be quite robust against violations of its basic assumptions for synthetic data with relatively large controlled deviations. It performs almost as well on real i...

This paper describes the development and testing of visual routines for vehicle control. It addresses the generation of visual routines from images using appearance based models of color and shape. The visual routines presented here are a major component of the perception subsystem of an intelligent vehicle. The idea of visual routines is compelling owing to the fact that being specialpurpose vast amounts of computation can be saved. For this reason they have been used in several simulations (eg. [9]), but so far they have been used in image analysis only in a few restricted circumstances.

To meet the demands of driving in complex environments, the perception subsystem of an intelligent vehicle must be able to extract the information needed for behaviors from the input video stream. An attractive way of achieving this is to have a library of basic image processing sub-functions (visual routines), which can be composed to subserve more elaborate goal-directed programs. The crucial compositional capability allows the visual routines to span the huge space of different task goals. The visual routines presented here are developed in a unique platform. The view from a car driving in a simulated world is fed into a Datacube pipeline video processor. The integration of photo-realistic simulation and real-time image processing represents a proof of concept for a new system design which allows testing computer vision algorithms under controllable conditions, thus leading to rapid prototyping. In addition to the simulations, the routines are also tested on similar images generated...

Human vision uses mechanisms of covert attention to selectively process interesting information and overt eye movements to extend this selectivity ability. Thus, visual tasks can be effectively dealt with by limited processing resources. Modelling visual attention for machine vision systems is not only critical but also challenging. In the machine vision literature there have been many conventional attention models developed but they are all space-based only and cannot perform object-based selection. In consequence, they fail to work in real-world visual environments due to the intrinsic limitations of the space-based attention theory upon which these models are built. The aim of the work presented in this thesis is to provide a novel human-like visual selection framework based on the object-based attention theory recently being developed in psychophysics. The proposed solution -- a Hierarchical Object-based Attention Framework (HOAF) based on grouping competition, consists of two closely-coupled visual selection models of (1) hierarchical object-based visual (covert) attention and (2) object-based attention-driven (overt) saccadic eye movements. The Hierarchical Object-based Attention Model (HOAM) is the primary selection mechanism and the Object-based Attention-Driven Saccading model (OADS) has a supporting role, both of which are combined in the integrated visual selection framework HOAF.