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.
Highlights
Advances in robotics, control theory, and digital imaging technology have enabled the collection of large-scale digital photographic data-sets for a large variety of ecological surveys[1,2,3,4]
We have recently developed the FluorIS (Fluorescence Imaging System)[22], a consumer camera modified for increased sensitivity of near-infrared wavelengths
We show that our Convolutional Neural Networks (CNN)-based method was able to utilize the additional information captured by FluorIS to significantly improve the annotation accuracy compared to methods which only utilized the reflectance images[6]
Summary
Control theory, and digital imaging technology have enabled the collection of large-scale digital photographic data-sets for a large variety of ecological surveys[1,2,3,4]. In the last three decades up to 80% of coral coverage has been lost in the Caribbean[11] and up to 50% in the Indo-Pacific[12,13] largely due to anthropogenic stressors including over-fishing, pollution, sedimentation, habitat destruction and climate change[14,15,16]. This accelerated rate of decline creates a need for rapid assessments of reef health in order to develop more effective management and conservation strategies[17]. As shown in this work, these difficulties can be alleviated by incorporating fluorescence information in the automated annotation methods
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
