Improving automated annotation of benthic survey images using wide-band fluorescence

Beijbom, Oscar, Treibitz, Tali, Kline, David I., Eyal, Gal, Khen, Adi, Neal, Benjamin, Loya, Yossi, Mitchell, B. Greg and Kriegman, David (2016) Improving automated annotation of benthic survey images using wide-band fluorescence. Scientific Reports, 6 . doi:10.1038/srep23166


Author Beijbom, Oscar
Treibitz, Tali
Kline, David I.
Eyal, Gal
Khen, Adi
Neal, Benjamin
Loya, Yossi
Mitchell, B. Greg
Kriegman, David
Title Improving automated annotation of benthic survey images using wide-band fluorescence
Journal name Scientific Reports   Check publisher's open access policy
ISSN 2045-2322
Publication date 2016-03-29
Year available 2016
Sub-type Critical review of research, literature review, critical commentary
DOI 10.1038/srep23166
Open Access Status DOI
Volume 6
Total pages 11
Place of publication London, United Kingdom
Publisher Nature Publishing Group
Collection year 2017
Language eng
Formatted abstract
Large-scale imaging techniques are used increasingly for ecological surveys. However, manual analysis can be prohibitively expensive, creating a bottleneck between collected images and desired data-products. This bottleneck is particularly severe for benthic surveys, where millions of images are obtained each year. Recent automated annotation methods may provide a solution, but reflectance images do not always contain sufficient information for adequate classification accuracy. In this work, the FluorIS, a low-cost modified consumer camera, was used to capture wide-band wide-field-of-view fluorescence images during a field deployment in Eilat, Israel. The fluorescence images were registered with standard reflectance images, and an automated annotation method based on convolutional neural networks was developed. Our results demonstrate a 22% reduction of classification error-rate when using both images types compared to only using reflectance images. The improvements were large, in particular, for coral reef genera Platygyra, Acropora and Millepora, where classification recall improved by 38%, 33%, and 41%, respectively. We conclude that convolutional neural networks can be used to combine reflectance and fluorescence imagery in order to significantly improve automated annotation accuracy and reduce the manual annotation bottleneck.
Keyword Large-scale imaging techniques
Ecological surveys
Wide-band fluorescence images
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Critical review of research, literature review, critical commentary
Collections: Global Change Institute Publications
HERDC Pre-Audit
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Sun, 24 Apr 2016, 10:28:09 EST by System User on behalf of Learning and Research Services (UQ Library)