BibTeX entry

@PHDTHESIS{201205Shoaib_Ehsan,
  AUTHOR={Shoaib Ehsan},
  TITLE={Improving the Effectiveness of Local Feature Detection},
  SCHOOL={University of Essex},
  MONTH=May,
  YEAR=2012,
  URL={http://www.bmva.org/theses/2012/2012-ehsan.pdf},
}

Abstract

The last few years have seen the emergence of sophisticated computer vision systems that target complex real-world problems. Although several factors have contributed to this success, the ability to solve the image correspondence problem by utilizing local image features in the presence of various image transformations has made a major contribution. The trend of solving the image correspondence problem by a three-stage system that comprises detection, description, and matching is prevalent in most vision systems today. This thesis concentrates on improving the local feature detection part of this three-stage pipeline, generally targeting the image correspondence problem. The thesis presents offline and online performance metrics that reflect real-world performance for local feature detectors and shows how they can be utilized for building more effective vision systems, confirming in a statistically meaningful way that these metrics work. It then shows how knowledge of individual feature detectors’ functions allows them to be combined and made into an integral part of a robust vision system. Several improvements to feature detectors’ performance in terms of matching accuracy and speed of execution are presented. Finally, the thesis demonstrates how resource-efficient architectures can be designed for local feature detection methods, especially for embedded vision applications.