Design of a low-cost and extensible acoustically-triggered camera system for marine population monitoring

Wilby, Antonella; Kastner, Ryan; Hostler, Andrew; Slattery, Ethan

doi:10.1109/oceans.2016.7761320

Cited by 4 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite recent advancements in underwater housings, image quality, and data storage, lowcost (i.e., <$5,000) optical imaging systems (OISs) are still challenged by power and light limitations (Balazy et al, 2018). Most battery-powered OISs that sample nearly continuously are only capable of a few hours of image or video capture (e.g., Favaro et al, 2012;Mallet and Pelletier, 2014;Wilby et al, 2016). OISs capable of longer deployments are often part of seafloor ocean observatories that are powered from shore (Aguzzi et al, 2011;Vardaro et al, 2013).…”

Section: Ntroductionmentioning

confidence: 99%

An Optical Imaging System for Capturing Images in Low-Light Aquatic Habitats Using Only Ambient Light

Pagniello¹,

Butler²,

Rosen³

et al. 2021

Oceanog

View full text Add to dashboard Cite

It is preferable that methods for monitoring fish behavior, diversity, and abundance be noninvasive to avoid potential bias. Optical imaging facilitates the noninvasive monitoring of underwater environments and is best conducted without the use of artificial lighting. Here, we describe a custom-designed optical imaging system that utilizes a consumer-grade camera to capture images in situ in ambient light. This diver-deployed system can be used to collect time series of occurrences of animals while concurrently obtaining behavioral observations for two weeks to a month (depending on the sampling rate). It has also been configured to be paired with a passive acoustic system to record time-synchronized image and acoustic data. The system was deployed in a protected kelp forest off southern California and captured >1,500 high-quality images per day over 14 days. The images revealed numerous fish species exhibiting biologically important behaviors as well as daily patterns of presence/absence. The optical imaging system is a cost-effective tool that can be easily fabricated and improves upon many of the limitations of previous systems, including deployment length and image quality in low-light and limited-visibility conditions. The system provides a relatively noninvasive way to monitor shallow marine habitats, including protected areas, and can augment traditional survey methods by providing nearly continuous observations and thus yield increased statistical power.

show abstract

Section: Ntroductionmentioning

confidence: 99%

An Optical Imaging System for Capturing Images in Low-Light Aquatic Habitats Using Only Ambient Light

Pagniello¹,

Butler²,

Rosen³

et al. 2021

Oceanog

View full text Add to dashboard Cite

show abstract

“…Contemporary visionbased robots, leverage both the mature understanding of visual geometry, e.g., (Diel, et al 2005), and the power of data-driven visual lookup, e.g., (Johns et al 2016). Moreover, vision and robotics together now support many other investigations, e.g., husbanding endangered marine species (Wilby, et al 2016), tracking lions in their natural habitat (Ackerman 2013), even surveilling other robots (Moeys et al 2016). To help undergraduates tap into these trends, we created and tested a software framework --for building and localizing within circular panoramas using vision.…”

Section: The Challengementioning

confidence: 99%

An Image Wherever You Look! Making Vision Just Another Sensor for AI/Robotics Projects

Zhang

Lee

Jones

et al. 2017

AAAI

View full text Add to dashboard Cite

Visual sensing can be difficult to incorporate into undergraduate robotics and AI assignments. Images, after all, do not provide a direct estimate of the geometric conditions within the field of view. Yet vision is increasingly compelling as a part of undergraduate AI and robotics, given the centrality of pixels in our students' interactions with technology and each other. This paper shares a small-footprint framework designed to make visual sensing as easy to incorporate into AI projects and assignments, e.g., as a source of evidence for localization algorithms, as range sensors. The framework leverages (hand-built) circular panoramas and the image-matching capabilities provided by OpenCV's python library. An example localization project highlights its pedagogical accessibility and ease of deployment atop low-cost hardware and alongside other sensors.

show abstract

“…Acoustic cameras [ 8 , 9 ] have been used in the past to image sharks and other fishes in low-light, turbid environments, replacing light-based imaging entirely [ 10 ] for species that are morphologically distinct enough to be differentiated in this manner [ 11 ]. This suggests that specific acoustic cues could also be used to trigger conventional optical cameras [ 12 ], although this would have limited applications outside of underwater camera trapping.…”

Section: Introductionmentioning

confidence: 99%

A low-cost, long-term underwater camera trap network coupled with deep residual learning image analysis

Bilodeau

Schwartz

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

Understanding long-term trends in marine ecosystems requires accurate and repeatable counts of fishes and other aquatic organisms on spatial and temporal scales that are difficult or impossible to achieve with diver-based surveys. Long-term, spatially distributed cameras, like those used in terrestrial camera trapping, have not been successfully applied in marine systems due to limitations of the aquatic environment. Here, we develop methodology for a system of low-cost, long-term camera traps (Dispersed Environment Aquatic Cameras), deployable over large spatial scales in remote marine environments. We use machine learning to classify the large volume of images collected by the cameras. We present a case study of these combined techniques’ use by addressing fish movement and feeding behavior related to halos, a well-documented benthic pattern in shallow tropical reefscapes. Cameras proved able to function continuously underwater at deployed depths (up to 7 m, with later versions deployed to 40 m) with no maintenance or monitoring for over five months and collected a total of over 100,000 images in time-lapse mode (by 15 minutes) during daylight hours. Our ResNet-50-based deep learning model achieved 92.5% overall accuracy in sorting images with and without fishes, and diver surveys revealed that the camera images accurately represented local fish communities. The cameras and machine learning classification represent the first successful method for broad-scale underwater camera trap deployment, and our case study demonstrates the cameras’ potential for addressing questions of marine animal behavior, distributions, and large-scale spatial patterns.

show abstract

Design of a low-cost and extensible acoustically-triggered camera system for marine population monitoring

Cited by 4 publications

References 11 publications

An Optical Imaging System for Capturing Images in Low-Light Aquatic Habitats Using Only Ambient Light

An Optical Imaging System for Capturing Images in Low-Light Aquatic Habitats Using Only Ambient Light

An Image Wherever You Look! Making Vision Just Another Sensor for AI/Robotics Projects

A low-cost, long-term underwater camera trap network coupled with deep residual learning image analysis

Contact Info

Product

Resources

About