Power haulage accounts for the greatest number of fatalities in Canadian, Australian, American, Indian, and Spanish mines, and is the fourth leading cause of fatal accidents in underground African mines. However, this rate is expected to grow with a move toward increased power haulage and less manual labour in Africa. Many of the fatal injuries have been associated with load-haul-dump (LHD) ope...

A trend in abdominal surgery is the transition from open procedures to minimally invasive laparoscopic interventions, where visual feedback to surgical staff is only available through the laparoscope camera and direct palpation of organs is impossible. To successfully perform such sophisticated interventions, the provision of additional intraoperative feedback can be of great help to the surgic...

of the printed circuit in the gripper is recorded beforehand by the bottom camera. This requires a visual check on a reference pin. There is yet another quality control and visual inspection, in case pins have broken off, before the component is placed in position. Finally, the built-in force sensor and programmed force control ensure that nothing is damaged during placement. Although some forc...

Localization with landmarks is a recurrent problem in robotics. In order to perceive the environment, robots are often equipped with some exteroceptive sensors (such as camera, laser range finder, etc). One way of using these sensors for localization is to detect some features in the environment and to use them as landmarks. In this paper, we present how we tackle the complete set up of a fast,...

A robotic system developed to manipulate ophthalmic lenses during the edging process is presented. The robot is assisted by a machine vision system to accurately determine the position and orientation of the lens optical center and axis, through the localization of two small fiducial marks on the lens surface. The optimal design of the j2ducial marks is investigated in order to minimize their s...

Generating films from 3D animations requires knowledge in cinematography (camera placement, framing and lighting) and editing (cutting between cameras). In applications where the user is already engaged in other tasks, such as playing a game, directing virtual actors, or narrating a story, it appears desirable to build systems that can make decisions about cinematography and editing and automat...

Animations generated by interactive 3D computer graphics applications are typically portrayed either from a particular character's point of view or from a small set of strategically-placed viewpoints. By ignoring camera placement, such applications fail to realize important storytelling capabilities that have been explored by cinematographers for many years. In this paper, we describe several o...

Enemy observers, such as cameras and guards, are common elements that provide challenge to many stealth and combat games. Defining the exact placement and movement of such entities, however, is a non-trivial process, requiring a designer balance level-difficulty, coverage, and representation of realistic behaviours. In this work we explore systems for procedurally generating both camera and gua...

We propose a novel approach to determining the Next Best View (NBV) for the task of efficiently building highly accurate 3D models from images. Our proposed method deploys a hierarchical uncertainty driven model refinement process designed to select vantage viewpoints based on the model’s covariance structure and appearance, as well as the camera characteristics. The developed NBV planning syst...

In this paper, we present a robust method to estimate the three-dimensional ego-motion of an observer moving in a static environment. This method combines the optical ow elds observed with multiple cameras to avoid the ambiguity of 3-D motion recovery due to small eld of view and small depth variation in the eld of view. Two residual functions are proposed to estimate the ego-motion for diieren...