Computational strategies for understanding underwater optical image datasets
Citable URI
https://hdl.handle.net/1912/6237DOI
10.1575/1912/6237Keyword
Remote submersibles; Image analysisAbstract
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.
Description
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 Citation
Thesis: Kaeli, Jeffrey W., "Computational strategies for understanding underwater optical image datasets", 2013-09, DOI:10.1575/1912/6237, https://hdl.handle.net/1912/6237Related items
Showing items related by title, author, creator and subject.
-
Fluxes, dynamics and chemistry of particulates in the ocean
Gardner, Wilford D. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1977-10)Sediment traps designed to yield quantitative data of particulate fluxes have been deployed and successfully recovered on four moorings in the deep sea. The traps were designed after extensive calibration of different ... -
Laboratory measurements of the sound generated by breaking waves
Loewen, Mark Richard (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1991-12)Breaking waves dissipate energy, transfer momentum from the wind to surface currents and breaking enhances the transfer of gas and mass across the air-sea interface. Breaking waves are believed to be the dominant source ... -
Dissolved inorganic and particulate iodine in the oceans
Wong, George T. F. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 1976-02)Analytical methods have been developed for the determination of iodate, iodide and particulate iodine in sea water. Iodate is converted to tri-iodide and the absorbance of tri-iodide at 353 nm is measured. The precision ...