Derya Akkaynak

2019 Regional Award Finalist — Post-Doc

Derya Akkaynak

Current Position:
Engineer

Institution:
Interuniversity Institute of Marine Sciences in Eilat (Previously Princeton University)

Discipline:
Atmospheric & Oceanic Sciences

Recognized for: Significant breakthroughs and advancements in computer vision and underwater imaging technologies, resolving a fundamental technological problem in the computer vision community—the reconstruction of lost colors and contrast in underwater photographic imagery—which will have real implications for oceanographic research.

Areas of Research Interest and Expertise: Underwater Imaging, Visual Ecology, Oceanography, Mechanical Engineering, Computer Vision

 


2019 Blavatnik Regional Awards Honorees in Physical Sciences & Engineering

Previous Positions:

Postdoctoral Fellow, University of Haifa & Interuniversity Institute of Marine Sciences, Israel
Fellow, Smithsonian Tropical Research Institute, Panama
PhD, Massachusetts Institute of Technology
MSc, Massachusetts Institute of Technology
BSc, Middle East Technical University, Turkey

Research Summary:

Dr. Derya Akkaynak is a mechanical engineer and oceanographer who is blurring the lines between oceanography, engineering, computer vision, and conservation. Her work has taken her all around the world, from icy Antarctic seas to wild islands in the Pacific, and she is changing the way scientists think about underwater research and conservation. As oceans face mounting pressures from pollution, climate change, and overfishing, conservation research efforts to protect endangered species and habitats have become crucially important. Dr. Akkaynak has resolved a fundamental physical problem that persisted within the computer vision community for decades, and correspondingly, has real implications for oceanographic research: the reconstruction of lost colors and contrast in underwater imagery. She has transformed the way the computer vision community understands light’s behavior underwater by taking into account (i) natural variations in light’s properties in ocean settings and (ii) the spectral sensitivities of underwater cameras. Armed with this information, Dr. Akkaynak can now accurately restore color and contrast in underwater images, which will enable efficient, automated analysis of underwater images, accelerating the pace of marine research. In addition, Dr. Akkaynak has developed a multi-spectral camera to see the underwater world from the perspective of marine animals, such as turtles and seabirds. This camera can in-effect help agencies like NOAA set appropriate guidelines for fishing gear, which kills millions of turtles annually. These technological developments are revolutionizing oceanographic research and will launch the field of marine science into the era of automated deep learning, finding widespread use in underwater exploration and conservation.

"I love my research and work very long hours. Often, nothing makes sense: equations don’t check out; results are counter-intuitive; or I am simply stuck. Those low moments lead to my best work. Reminding myself that “Discovery is seeing what everybody has seen and thinking what nobody has thought - Albert Szent-Györgyi”, I force myself to stop, release my current mindset, and search for a brand new perspective. And I find one every time."

Key Publications:

  1. D. Akkaynak, and T. Treibitz. Sea-Thru: A Method for Removing Water From Underwater Images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019.
  2. D. Akkaynak, and T. Treibitz. A Revised Underwater Image Formation Model. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6723-6732. 2018.
  3. D. Akkaynak, T. Treibitz, T. Shlesinger, Y. Loya, R. Tamir, D. Iluz. What is the Space of Attenuation Coefficients in Underwater Computer Vision? In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.
  4. D. Akkaynak, T. Treibitz, B. Xiao, U.A. Gürkan, J.J. Allen, U. Demirci, R.T. Hanlon. Use of Commercial off-the-shelf Digital Cameras for Scientific Data Acquisition and Scene-specific Color Calibration. Journal of the Optical Society A, 2014.

Other Honors:

2018 International Ocean Color Coordinating Group Summer Lecture Series travel award (France)
2018 IEEE CVPR Women in Computer Vision travel award

In the Media:

New York Times - Why Do Bird Eggs Have Different Shapes? Look to the Wings

New York Times - Battle of Cuttlefish Caught on Tape

National Geographic - Through a Shark's Eyes: See How They Glow in the Deep

EUMETSAT - Ocean colour satellites can be used to measure light attenuation in the water column – a crucial factor when processing images

In The DeepSeeing the Ocean Through Alien Eyes

Hakai Magazine -- Do You See What Eye See?

Personal Website

Princeton Website