Alistair Greig

An EM/E-MRF algorithm for adaptive model based tracking in extremely poor visibility

This paper addresses the problems of visual tracking in conditions of extremely poor visibility. The human visual system can often correctly interpret images that are of such poor quality that they contain insufficient explicit information to do so. We assert that such systems must therefore make use of prior knowledge in several forms. A tracking algorithm is presented which combines observed data (the current image) with predicted data derived from prior knowledge of the object being viewed and an estimate of the cameras motion. During image segmentation, a predicted image is used to estimate class conditional distribution models and an Extended-Markov Random Field technique is used to combine observed image data with expectations of that data within a probabilistic framework. Interpretations of scene content and camera position are then mutually improved using Expectation Maximisation. Models of background and tracked object are continually relearned and adapt iteratively with each new image frame. The algorithm is tested using real video sequences, filmed in poor visibility conditions with complete pre-measured ground-truth data.

Making shipping greener: comparative study between organic fluids and water for Rankine cycle waste heat recovery

The largest source of energy loss in ships is found in the propulsion system. This study focuses on the concept of managing waste heat energy from the exhaust gases of the main engine. Using waste heat recovery systems (WHRSs) to make shipping more efficient represents a good area of opportunity for achieving the shipping industrys green objectives. Organic Rankine cycles have been applied in land-based systems before, showing improvements in performance when compared with the traditional Rankine cycle. As marine environmental rules requiring greener vessels and engine thermal efficiency continue to increase, thus reducing the available energy in the exhaust, organic Rankine cycle WHRSs become a more attractive option.The proposed WHRS was modelled using MATLAB for a typical ship installation with a slow speed diesel engine and a WHRS installed after the steam boiler in the exhaust gas system. The energy recovered from the exhaust gas flow is transformed via the thermodynamic cycle – coupled with a generator – into electricity, which helps to cover the ships demand. The MATLAB code found the highest electric power output, hence the maximum fuel and CO2 emission savings possible, by v varying the WHRS HP. Water and four organic fluids were considered and their performance was compared over a range of different engine operating conditions. A representative ship operating profile and a typical marine generator were used to measure CO2 emission reductions. The implications of having flammable organic fluids on board are also briefly discussed. This work demonstrates that a simple organic Rankine cycle can be more effective than a steam cycle for the same engine operating conditions.

A calibration system for measuring 3D ground truth for validation and error analysis of robot vision algorithms

An important task in robot vision is that of determining the position, orientation and trajectory of a moving camera relative to an observed object or scene. Many such visual tracking algorithms have been proposed in the computer vision, artificial intelligence and robotics literature over the past 30 years. However, it is seldom possible to explicitly measure the accuracy of these algorithms, since the ground-truth camera positions and orientations at each frame in a video sequence are not available for comparison with the outputs of the proposed vision systems. A method is presented for generating real visual test data with complete underlying ground truth. The method enables the production of long video sequences, filmed along complicated six-degree-of-freedom trajectories, featuring a variety of objects and scenes, for which complete ground-truth data are known including the camera position and orientation at every image frame, intrinsic camera calibration data, a lens distortion model and models of the viewed objects. This work encounters a fundamental measurement problem—how to evaluate the accuracy of measured ground truth data, which is itself intended for validation of other estimated data. Several approaches for reasoning about these accuracies are described.

Welding automation in space-frame bridge construction

The SPACES system has been proposed as an alternative for long-span bridge construction. Tubular space frames offer a structurally more efficient solution for bridges, but they have been considered too expensive because the joints at the nodal intersections of the tubular members are difficult and expensive to weld. The benefits of the SPACES system can only be realized by using a computer-integrated construction system to drive down the fabrication costs. A key component of the computer-integrated construction is the robotic welding system. This article describes the development of a lightweight automated welding system for the joining of tubular members. It addresses the geometry of intersecting cylinders and the kinematics and design of a 5-degree-of-freedom manipulator: Summary solutions are given for both. The control software is described briefly, and mention of the welding tests and overall business process is also made. A consortium of U.K. industry and universities is conducting the work.

Video with ground-truth for validation of visual registration, tracking and navigation algorithms

A fundamental task in computer vision is that of determining the position and orientation of a moving camera relative to an observed object or scene. Many such visual tracking algorithms have been proposed in the computer vision, artificial intelligence and robotics literature over the past 30 years. Predominantly, these remain un-validated since the ground-truth camera positions and orientations at each frame in a video sequence are not available for comparison with the outputs of the proposed vision systems. A method is presented for generating real visual test data with complete underlying ground-truth. The method enables the production of long video sequences, filmed along complicated six degree of freedom trajectories, featuring a variety of objects, in a variety of different visibility conditions, for which complete ground-truth data is known including the camera position and orientation at every image frame, intrinsic camera calibration data, a lens distortion model and models of the viewed objects.

Extended Markov Random Fields for Predictive Image Segmentation

Since the 1970s, there has been increasing interest in the use of Markov Random Fields (MRFs) as models to aid in the segmentation of noisy or degraded digital images. MRFs can make up for deficiencies in observed information by adding a-priori knowledge to the image interpretation process in the form of models of spatial interaction between neighbouring pixels. In data fusion problems, interaction might also be assumed between corresponding pixels in two different kinds of image of the same scene. Alternatively, temporal interaction might be assumed between corresponding pixels in consecutive frames of a video sequence. In object tracking or robotic navigation problems, a similar relationship may exist between pixels of an observed image and those of a predicted image, derived from models of the motion and scene. In all of these cases the MRF model can be extended to incorporate this additional knowledge. This paper explains the theory of Extended-Markov Random Field (E-MRF) segmentation techniques, surveys the research which has been crucial to their development and presents results from new work in this area with an application to robotic vision in conditions of extremely poor visibility.

Some Problems in Trying to Implement Uncertainty Techniques in Automated Inspection

This paper discusses the difficulties in applying uncertainty management techniques to real world problems. Automated Inspection is a process where the data used to model the environment is uncertain. There is an existing body of knowledge within the research community which enables such uncertain information to be expressed. Although there have been successful applications in fields such as medical diagnosis, there are also problems in industry which currently cannot be solved. The process of industrial inspection is an environment where the method for applying uncertainty management techniques is not intuitive. The nature of the uncertainty and the difficulty in applying the theoretical techniques to real world problems shall be the focus of the following discussion.

Comparing Trimaran Small Waterplane Area Center Hull (TriSWACH), Monohull, and Trimaran Hullforms: Some Initial Results

Alternative hullforms such as multihulls may allow small vessels to deliver levels of performance normally associated with a far larger and more costly monohull vessel. This article describes a research program on alternative hullforms being undertaken by a consortium of six universities and academic institutions. As well as reviewing the current research program, this article discusses in detail the contribution being made by University College London (UCL): tools for undertaking the comparison and exploration of the monohull, trimaran, and Trimaran Small Waterplane Area Center Hull (TriSWACH) alternatives. These tools combine the modeling and analysis capabilities of an existing naval architecture design package with a varied range of search and optimization techniques to enable the exploration of alternative ship design solutions. This article presents the initial results obtained from tools that are currently under development at UCL. Such tools can be applied to identify and explore key topics related to the trimaran and TriSWACH hullforms when compared with a baseline monohull configuration. The trimaran hullform has significant potential for small fast combatants as demonstrated by the U.S. Navys LCS program. The TriSWACH hullform (with a small waterplane area centerhull stabilized by two outriggers) is of interest because it offers the potential for improved seakeeping performance.

Application of the Hough Transform for Weld Inspection Underwater

The inspection of the nodal welds of off-shore steel structures is a necessary but hazardous task at present performed at regular intervals by divers. Automation of this task is an on-going research effort. One requirement for automation is the accurate location of the weld roots and it is this which is considered here. A brief description of the system is provided as well as a summary of the problems of imaging underwater. This is followed by a description of how the relevant segments of the degraded laser stripe can be identified using the Hough transform. The Rainflow method (originally proposed by Tatsuo Endo for analysis of stress histories) is then used to rapidly identify the desired features on the parameter surface and hence locate the weld roots.