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.
-
Internal hydraulic jumps with upstream shear
Ogden, Kelly A. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2017-02)Internal hydraulic jumps in flows with upstream shear are investigated numerically and theoretically. The role of upstream shear has not previously been thoroughly investigated, although it is important in many oceanographic ... -
Insight into chemical, biological, and physical processes in coastal waters from dissolved oxygen and inert gas tracers
Manning, Cara C. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2017-02)In this thesis, I use coastal measurements of dissolved O2 and inert gases to provide insight into the chemical, biological, and physical processes that impact the oceanic cycles of carbon and dissolved gases. Dissolved ... -
Coral biomineralization, climate proxies and the sensitivity of coral reefs to CO2-driven climate change
DeCarlo, Thomas M. (Massachusetts Institute of Technology and Woods Hole Oceanographic Institution, 2017-02)Scleractinian corals extract calcium (Ca2+) and carbonate (CO2−3) ions from seawater to construct their calcium carbonate (CaCO3) skeletons. Key to the coral biomineralization process is the active elevation of the CO2−3 ...