Computational strategies for understanding underwater optical image datasets
Kaeli, Jeffrey W.
MetadataShow full item record
A fundamental problem in autonomous underwater robotics is the high latency between the capture of image data and the time at which operators are able to gain a visual understanding of the survey environment. Typical missions can generate imagery at rates hundreds of times greater than highly compressed images can be transmitted acoustically, delaying that understanding until after the vehicle has been recovered and the data analyzed. While automated classification algorithms can lessen the burden on human annotators after a mission, most are too computationally expensive or lack the robustness to run in situ on a vehicle. Fast algorithms designed for mission-time performance could lessen the latency of understanding by producing low-bandwidth semantic maps of the survey area that can then be telemetered back to operators during a mission. This thesis presents a lightweight framework for processing imagery in real time aboard a robotic vehicle. We begin with a review of pre-processing techniques for correcting illumination and attenuation artifacts in underwater images, presenting our own approach based on multi-sensor fusion and a strong physical model. Next, we construct a novel image pyramid structure that can reduce the complexity necessary to compute features across multiple scales by an order of magnitude and recommend features which are fast to compute and invariant to underwater artifacts. Finally, we implement our framework on real underwater datasets and demonstrate how it can be used to select summary images for the purpose of creating low-bandwidth semantic maps capable of being transmitted acoustically.
Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy at the Massachusetts Institute of Technology and the Woods Hole Oceanographic Institution September 2013
Suggested CitationThesis: Kaeli, Jeffrey W., "Computational strategies for understanding underwater optical image datasets", 2013-09, DOI:10.1575/1912/6237, https://hdl.handle.net/1912/6237
Showing items related by title, author, creator and subject.
Bowen, Melissa M. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2000-02)The variability of salt transport determines the variation of the length of the salinity intrusion and the large-scale density gradient in an estuary. This thesis contains three studies that address salt transport and ...
A radiocarbon method and multi-tracer approach to quantifying groundwater discharge to coastal waters Gramling, Carolyn M. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2003-09)Groundwater discharge into estuaries and the coastal ocean is an important mechanism for the transport of dissolved chemical species to coastal waters. Because many dissolved species are present in groundwater in ...
Surface exposure geochronology using cosmogenic nuclides : applications in Antarctic glacial geology Brook, Edward J. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1993-09)Cosmogenic 3He, 26A1, and 10Be have been measured in a variety of Antarctic glacial deposits in the McMurdo Sound-Dry Valleys region. The goals of this project were to provide age constraints for Antarctic glacial events, ...