| Calibration, Recognition, and Shape from Silhouettes of Stones | Keith Forbes
PhD thesis
University of Cape Town
June 2007 |
Abstract: Multi-view shape-from-silhouette systems are increasingly used for analysing stones. This thesis presents methods to estimate stone shape and to recognise individual stones from their silhouettes. Calibration of two image capture setups is investigated. First, a setup consisting of two mirrors and a camera is introduced. Pose and camera internal parameters are inferred from silhouettes alone. Second, the configuration and calibration of a high throughput multi-camera setup is covered. Multiple silhouette sets of a stone are merged into a single set by inferring relative poses between sets. This is achieved by adjusting pose parameters to maximise geometrical consistency specified by the epipolar tangency constraint. Shape properties (such as volume, flatness, and elongation) are inferred more accurately from the merged silhouette sets than from the original silhouette sets. Merging is used to recognise individual stones from pairs of silhouette sets captured on different occasions. Merged sets with sufficient geometrical consistency are classified as matches (produced by the same stone), whereas inconsistent sets are classified as mismatches. Batch matching is determining the one-to-one correspondence between two unordered batches of silhouette sets of the same batch of stones. A probabilistic framework is used to combine recognition by merging (which is slow, but accurate) with the efficiency of computing shape distribution-based dissimilarity values. Two unordered batches of 1200 six-view silhouette sets of uncut gemstones are correctly matched in approximately 68~seconds (using a 3.2GHz Pentium 4 machine). An experiment that compares silhouette-based shape estimates with mechanical sieving demonstrates an application using the developed methods. A batch of 494 garnets is sieved 15 times. After each sieving, silhouette sets are captured for sub-batches in each bin. Batch matching is used to determine the 15 sieve bins per stone. Better estimates of repeatability, and better understanding of the variability of the sieving process is obtained than if only histograms (the natural output of sieving) were considered. Silhouette-based sieve emulation is found to be more repeatable than mechanical sieving. | Full thesis (36.7MB PDF file, print resolution)
1st half of thesis (3.0MB PDF file, screen resolution)
2nd half of thesis (4.7MB PDF file, screen resolution) |
| Using colour features to classify objects and people in a video surveillance network | Mathew Price
MSc thesis
University of Cape Town
March 2004 | Abstract: Visual tracking of humans has proved to be an extremely challenging task for computer
vision systems. One idea towards the development of these systems is the
incorporation of colour. Often the colour appearance of a person can provide enough
information to identify an object or person in the short-term. However, the imprecise
nature of colour measurements typically encountered in image processing has limited
their use. This thesis presents a system which uses the colour appearances of objects
and people for tracking across multiple camera views in a digital video surveillance
network. A distributed framework for creating and sharing visual information between
several cameras is suggested, including a simple method for generating relative colour
constancy. Tracking has been approached from a classification standpoint allowing
the system to cope with multiple occlusions, variable camera pose, and asynchronous
video feeds. Several test cases exhibiting various surveillance scenarios are used to
assess system performance, which is determined via some well-known surveillance
metrics. The system exhibits an average tracker detection rate of approximately 80%
with a false alarm rate of less than 2%. It is envisaged that the combination of the
presented system and motion estimation tracking techniques could eventually result
in a robust, real-time tracking system. | Full thesis (7.8MB PDF file)
Summary paper (1MB PDF file) |
|
|
Last Updated on Thursday, 22 January 2009 14:19 |
