Australian sea-floor survey data, with images and expert annotations

Bewley, Michael; Friedman, Ariell; Ferrari, Renata; Hill, Nicole; Hovey, Renae K.; Barrett, Neville S.; Marzinelli, Ezequiel M.; Pizarro, Oscar; Figueira, Will F.; Meyer, Lisa; Babcock, Russ; Bellchambers, Lynda M.; Byrne, Maria; Williams, Stefan B.

doi:10.1038/sdata.2015.57

Cited by 40 publications

(31 citation statements)

References 21 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This Australian benthic data set (Benthoz15) [33] consists of an expert-annotated set of geo-referenced benthic images and associated sensor data. These images were captured by AUV Sirius during Australias integrated marine observation system (IMOS) benthic monitoring program at multiple temperate locations ( Table 2) around Australia [8].…”

Section: Benthoz15 Datasetmentioning

confidence: 99%

Automatic Hierarchical Classification of Kelps Using Deep Residual Features

Mahmood

Ospina

Bennamoun

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, like kelps. This paper presents an automatic hierarchical classification method to classify kelps from images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned image representations extracted from deep residual networks. These powerful and generic features outperform the traditional off-the-shelf CNN features, which have already shown superior performance over the conventional hand-crafted features. Experi- ments also demonstrate that the hierarchical classification method outperforms the common parallel multi-class classifications by a significant margin. Experimental results are provided to illustrate the efficient applicability of the proposed method to study the change in kelp cover over time for annually repeated AUV surveys.

show abstract

Section: Benthoz15 Datasetmentioning

confidence: 99%

Automatic Hierarchical Classification of Kelps Using Deep Residual Features

Mahmood

Ospina

Bennamoun

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…1. The training image set consists of images from multiple locations in Western Australia, a subset of Benthoz15 dataset [23]. These images are used to train a deep network which then classifies unlabelled images and mosaics.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Fig. 2 shows the path followed by the Sirius AUV [23] to capture the coral reef and some sample images. A marine expert was added in the loop to validate the labels assigned by this classifier.…”

Section: B Unlabelled Mosaics and Coral Mapsmentioning

confidence: 99%

“…This Australian benthic data set (Benthoz15) [23] consists of an expert-annotated set of georeferenced benthic images and associated sensor data, captured by an autonomous underwater vehicle (AUV) around Australia. The whole dataset contains 407,968 expert labelled points, on 9,874 distinct images collected at different depths from nine sites around Australia over the past few years.…”

Section: A Benthoz15 Datasetmentioning

confidence: 99%

“…The activation vectors of the first fully connected layer of a pretrained VGGnet [24] are employed as feature representations in our work. The weights of this deep network are fine tuned using the Benthoz15 dataset [23] which consists of expertannotated and geo-referenced marine images from Australian seas.…”

Section: A Classification Processmentioning

confidence: 99%

See 2 more Smart Citations

Automatic annotation of coral reefs using deep learning

Mahmood

Bennamoun

et al. 2016

OCEANS 2016 MTS/IEEE Monterey

View full text Add to dashboard Cite

Abstract-Healthy coral reefs play a vital role in maintaining biodiversity in tropical marine ecosystems. Deep sea exploration and imaging have provided us with a great opportunity to look into the vast and complex marine ecosystems. Data acquisition from the coral reefs has facilitated the scientific investigation of these intricate ecosystems. Millions of digital images of the sea floor have been collected with the help of Remotely Operated Vehicles (ROVs) and Autonomous Underwater Vehicles (AUVs). Automated technology to monitor the health of the oceans allows for transformational ecological outcomes by standardizing methods for detecting and identifying species. Manual annotation is a tediously repetitive and a time consuming task for marine experts. It takes 10-30 minutes for a marine expert to meticulously annotate a single image. This paper aims to automate the analysis of large available AUV imagery by developing advanced deep learning tools for rapid and large-scale automatic annotation of marine coral species. Such an automated technology would greatly benefit marine ecological studies in terms of cost, speed, accuracy and thus in better quantifying the level of environmental change marine ecosystems can tolerate. We propose a deep learning based classification method for coral reefs. We also report the application of the proposed technique towards the automatic annotation of unlabelled mosaics of the coral reef in the Abrolhos Islands, Western Australia. Our proposed method automatically quantifies the coral coverage in this region and detects a decreasing trend in coral population which is in line with conclusions by marine ecologists.

show abstract

Robotic Coral Reef Health Assessment Using Automated Image Analysis

Manderson

Dudek

et al. 2016

Journal of Field Robotics

View full text Add to dashboard Cite

This paper presents a system capable of autonomous surveillance and analysis of coral reef ecosystems using natural lighting. We describe our strategy to safely and effectively deploy a small marine robot to inspect a reef using its digital cameras. Image analysis using a (RBF‐SVM) radial basis function‐support vector machines in combination with (LBP) local binary pattern, Gabor and Hue descriptors developed in this work are able to analyze the resulting image data automatically and reliably by learning from the annotations of expert marine biologists. Our primary evaluation is performed on a novel coral data set that we collected during a series of robotic ocean deployments, the MRL Coral Identification Challenge. We have also applied our algorithms to a data set of coral imagery previously published by other researchers. Our algorithms recognize coral images in our own challenging data with 88.9% accuracy, while being sufficiently efficient to run online on our vehicle. This demonstrates the feasibility of such a system for practical use for the preservation of this crucial ecological resource.

show abstract

Australian sea-floor survey data, with images and expert annotations

Cited by 40 publications

References 21 publications

Automatic Hierarchical Classification of Kelps Using Deep Residual Features

Automatic Hierarchical Classification of Kelps Using Deep Residual Features

Automatic annotation of coral reefs using deep learning

Robotic Coral Reef Health Assessment Using Automated Image Analysis

Contact Info

Product

Resources

About