The Computer Vision working group develops techniques and methods for the automated analysis of underwater video and still imagery. The need for automated analysis is particularly motivated by camera installations on seafloor cabled observatories such as NEPTUNE and VENUS which offer a 24/7 presence, resulting in unprecedented volumes of visual data. Scheduled recordings of underwater video data and static images are gathered with Internet-connected fixed and pan-tilt-zoom mounted cameras, which record data which can be used to analyze a variety of biological processes.
The analysis of underwater imagery imposes a series of unique challenges, which need to be tackled by the computer vision community in collaboration with biologists and ocean scientists. Topics of interest include, but are not limited to:
- underwater image enhancement
- physical models of reflectance and light transport
- underwater scene understanding
- classification, detection, segmentation
- autonomous underwater navigation
- detection and monitoring of marine life
- object tracking
- automatic video annotation and summarization
- context-aware machine learning and image understanding
| WG Main Projects | Initiated | Principal Investigators | Graduate students (HQP) |
|---|---|---|---|
| Detection of stationary animals in video | Jan 2014 | Alexandra Branzan Albu, Maia Hoeberechts | Marzieh Mernejad |
| Classification of seafloor substrates | June 2015 | Marlene Jeffries, Alexandra Branzan Albu, Maia Hoeberechts | Arnold Kalmbach |
| Automated QA/QC for video data | May 2015 | Alice Olga Victoria Bui, Marlene Jeffries, Alexandra Branzan Albu, Maia Hoeberechts | Tanmana Sadhu |
| Automated detection of floating obstacles | Sept 2014 | Alexandra Branzan Albu, Maia Hoeberechts, David Capson | Tanmana Sadhu |
| Publications by the Working Group |
|---|
André Mendes, Maia Hoeberechts and Alexandra Branzan Albu, “Evolutionary computational methods for optimizing the classification of sea stars in underwater images.” 1st Workshop on Automated Analysis of Video Data for Wildflife Surveillance, Wailoloa Beach, HI, USA, Jan. 9, 2015. Ryan Fier, Alexandra Branzan Albu and Maia Hoeberechts, “Automatic Fish Counting System for Noisy Deep-Sea Videos.” MTS/IEEE Oceans 2014, St. John’s, NL, Sept. 14-19, 2014. Alexandra Branzan Albu, Marzieh Mehrnejad, Maia Hoeberechts and David Capson, “Detection of Stationary Animals in Deep-Sea Video.” MTS/IEEE Oceans 2013, San Diego, CA, Sept. 23-26, 2013. Aleya Gebali, Detection of salient events in large datasets of underwater video. MSc Thesis, University of Victoria, 2012. Aleya Gebali, Alexandra Branzan Albu and Maia Hoeberechts, “Detection of Salient Events in Large Datasets of Underwater Video.” MTS/IEEE Oceans 2012, Hampton Roads, VA, Oct. 15-19, 2012 Jacopo Aguzzi, Corrado Costa, Katleen Robert, Marjolaine Matabos, Francesca Antonucci, S. Kim Juniper, Paolo Menesatti, “Automated image analysis for the detection of benthic crustaceans and bacterial mat coverage using the VENUS undersea cabled network” Sensors, Volume: 11, Issue: 11, 2011. |
test
ONC Staff managing this group:
(contact one of us if you wish to become part of this working group)
The content of this macro can only be viewed by users who have logged in.
The content of this macro can only be viewed by users who have logged in.
The content of this macro can only be viewed by users who have logged in.
This group is interested in:
-
A-D
-
E-L
-
M-R
-
S-V
-
W-Z
Document repository (shared documents - accessible only by participants):
