Coral reefs are rapidly degrading under the pressure of increasing human activities, and at a faster pace than our current actions to prevent further the degradation. Comprehensive and fully comparable information about the state of coral reefs is urgently needed to provide timely advice to management authorities. Under these premises, rapid and standardised survey technologies at a global scale are needed to provide such information and complement current regional efforts. The XL Catlin Seaview Survey combines existing technologies to merge efforts for a high quality and standardised approach.


The XL Catlin Seaview Survey approach is centred on high definition imagery, to document and study coral reefs worldwide. Based on the concept that ‘a picture is worth a thousand words’, this scientific survey is looking at extracting valuable information from coral reef imagery while archiving an unbiased proof of the condition of surveyed reefs. This approach involves rapid acquisition of high-resolution imagery over large extensions of reefs. Using computer vision and machine learning technologies, the imagery is rapidly analysed for coral reef structure across multiple spatial scales, from metres to kilometres.


The XL Catlin Seaview SVII camera was specially built for this project. It is designed to be a highly robust underwater vehicle capable of taking 360° high-resolution images in almost all weather conditions whilst on lengthy remote expeditions. A timer triggers the camera allowing it to take pictures at three-second intervals, which is controlled by an Android tablet, encased in an underwater housing. The head of the camera is designed to remain sealed whilst on expedition to avoid flooding issues – data and power are transferred through a wet link docking station.

Collection of Shallow Reef Survey Imagery

Lead scientist – Dr Manuel Gonzalez-Rivero


Using diver-propelled vehicles and customised HD cameras (SVII), divers survey unprecedented areas of coral reef over multiple reef sites. A depth sensor logger carried by the diver monitors the survey depth every second. Surveys are set to a standard depth of 10 metres (+/- 2 metres) following the contour of the reef at this depth. By standardising the survey depth, we avoid the inclusion of confounding factors (i.e. light, wave energy) when comparing the structure of coral reef communities amongst multiple spatial scales.

During the survey, the SVII camera captures three high-definition images every three seconds during the fifty minute dive. These images allow us to continuously record the full 360° environment along a 2 kilometres stretch of reef.

The transect location is selected by looking at capturing a vast variety of coral reef configurations or habitats to best represent the fore-reefs of a region.


This variability is captured by looking at multiple drivers of coral reef structure, such as environmental regimes (i.e. hurricane incidence, temperature regimes, ocean colour, etc.), local information, geomorphology (atoll, fringing reef, barrier reefs) as well as anthropogenic influence (i.e. coastal development, fishing pressure).

Every image captured for the XL Catlin Global Reef Record has a geographical tag that allows us to accurately describe a specific section of reef that can be revisited in time and compared against previous available information. To achieve this, a GPS unit is synchronised in time to the SVII cameras and tethered from the surface by the divers.

In order to accurately and consistently locate the benthic community structure, image scale is required to standardise the area of the reef to be analysed. A customised altitude logger has been fitted to the SVII camera, which is also synchronised to the time of the SVII cameras. This altimeter, connected to a doppler transducer, logs the altitude of the camera with respect to the seabed and depth. Using this information and the optical properties of the lens of the SVII camera, the footprint area of each downward facing camera is estimated.

Thus the Global Reef Record provides two main image data-products. The first product is qualitative 360° panoramas of the reef. The panoramas are created by scaling and stitching the fish-eye imagery and provide an interactive way to explore the complete environment of a reef. The second product is a quantitative analysis of benthic categories (% covers) along the reef transects. To generate these covers, from each downward facing image are obtained quadrats with features required for image analysis (colour corrected and cropped quadrats of ~1x 1 m). The image quadrats are re-scaled to fixed pixel / cm ratio and then automatically annotated as detailed next.

Estimating covers of benthic categories

Lead scientists – Dr Oscar Beijbom and Dr Manuel Gonzalez-Rivero

Every field campaign provides about 30-40 thousand survey images which need to be annotated in order to extract benthic cover estimates (e.g. % cover of coral, algae, & sand). Unfortunately, manual annotation of a human expert requires at least 10 minutes per quadrat, which creates a huge bottleneck between collected images and the required data-product (i.e. 30.000 images would take 3 years to annotate). To address this we have developed state-of-the art automated image annotation methods based on deep neural networks.

A random subset of the obtained quadrats for each region is first manually annotated using the random point annotation tool of CoralNet ( This data is then used to train deep neural networks that map image patches to key benthic categories. Label sets of benthic categories have been established based on their functional relevance to coral reef ecosystems and their ability to be reliably identified from images by human annotators. The labels are grouped into main benthic functional components depending on the coral region.
Names and descriptions of labels can be seen here.

Benthic categories employed for the classification of coral reefs quadrats in the Great Barrier Reef (GBR) and Coral Sea Commonwealth Marine Reserve (CSCMR), Australia.

Functional GroupLabelDescription
AlgaeCrustose coralline algaeCrustose coralline algae
AlgaeMacroalgaeUpright macroalgae > 1 cm in height (all genus and species) including cyanobacteria films
AlgaeTurf algaeMulti-specific algal assemblage of 1 cm or less in height
CoralAcroporidae branchingFamily Acroporidae, branching morphology (excluding hispidose type branching).
CoralAcroporidae hispidoseFamily Acroporidae, hispidose morphology
CoralOther AcroporidaeOther corals from the family Acroporidae (e.g., Isopora)
CoralAcroporidae plate or encrustingFamily Acroporidae, plate and encrusting morphologies
CoralAcroporidae table, corymbose or digitateFamily Acroporidae, table, corymbose and digitate morphologies
CoralFavidae or Mussidae, massive or meandroidFamilies Favidae and Mussidae, massive and meandroid morphologies
CoralOther hard coralOther hard coral including all other groups not represented by the other coral categories of this label set
CoralPocilloporidaeFamily Pocilloporidae
CoralPoritidae branchingFamily Poritidae, branching morphology
CoralPoritidae encrustingFamily Poritidae, encrusting morphology
CoralPoritidae massiveFamily Poritidae, massive morphology
OtherSandUnconsolidated reef sediment
OtherUnclear substrateUnclear, cannot make any ID
Other InvertebratesOther sessile invertebratesOther sessile invertebrates, zoanthids, anemones, clams, tunicates , etc.
Soft CoralAlcyoniidaeSoft coral, family Alcyoniidae, genera Lobophytum and Sarcophyton
Soft CoralSea fans and plumesSea fans and plumes
Soft CoralOther soft coralOther soft-corals, outside of the common Alcyoniidae and sea fans plumes

Benthic categories employed for the classification of coral reefs quadrats in the Caribbean

Functional GroupLabelDescription
AlgaeMacroalgaeUpright macroalgae > 1 cm in height (all genus and species) including cyanobacteria films
AlgaeTurf and crustose coralline algaeMulti-specific assemblages of filamentous algae and CCA smothering reef surface 1 cm or less in height
CoralAcropora cervicornisAcropora cervicornis
CoralAcropora palmataAcropora palmata
CoralAgaricia,Undaria,Leptoserisspp.Agariciidae, plates and encrusting corals of the genus Agaricia, Undaria and Helioseris
CoralColpophyllia natansColpophyllia natans
CoralCoral meandroidHard coral meandroid including Dendrogyra, Isophyllia, Manicina, Mycetophyllia, Musa, Scolymia
CoralCoral submassiveHard coral sub-massive, including Dichocoenia, Favia, Solenastrea, Stephanocoenia
CoralDiploria labyrinthiformisDiploria labyrinthiformis
CoralEusmilia fastigiataEusmilia fastigiata
CoralMadracis sp.Madracis sp.
CoralMeandrina sp.Meandrina sp.
CoralMontastraea cavernosaMontastraea cavernosa
CoralOrcbicella complexOrbicella complex, O. Annularis, O. faveolata, O. franksi
CoralPorites astreoidesPorites astreoides
CoralPorites branchingP. porites,P. divaricata,P. furcata
CoralPseudodiploria sp.P. strigosa, P. clivosa
CoralSiderastrea sidereaSiderastrea siderea
MilleporaMilleporaMillepora sp.
OtherOther, invertebrates, fishOther sessile and mobile invertebrates, fish
OtherSandUnconsolidated reef sediment
OtherTerrigenous sedimentsTerrigenous sediments
OtherUnclearUnclear, cannot make any ID
Soft CoralOther soft coralsOther soft corals including erect and encrusting forms
Soft CoralSea fansSea fans ,Gorgonia sp.
Soft CoralSea plumesSea plumes and whips
SpongeAplysina fistularisAplysina fistularis
SpongeCallyspongia vaginalisCallyspongia vaginalis
SpongeCliona viridis complexCliona viridis complex
SpongeEncrusting sponges< 5 cm height (for whole individual); e.g. S. ruetzlen, Haliclona sp.,Monanchora sp., Chondrilla sp., Clathria sp., C. varians
SpongeErect sponges>1 cm height; height >>basal area; projections include: upright narrow tubes, branches, arborescent, e.g.A. compressa
SpongeIrcinia sp.e.g. I. felix, I. strobilina
SpongeMassive spongesLarge basal area to body size and height > 5 cm; compact shape; irregular shapes include: chain-tubes, spherical, castle; e.g.E. ferox,Verongulasp.
SpongeOther spongesOther sponges (undfined to species/morphology): e.g. A. wiedenmayeri,Niphates sp.
SpongeRope spongesHeight >> basal area; Spread along the substrate, e.g.S. aura
SpongeTube spongesGrouped tube species: A. archeri, A. tubulata, C. plicifera, N. digitalis, unknown vase and small barrel group (tube openining ~ height; basal area < opening)
SpongeXestospongia mutaXestospongia muta

To validate our method we generated automated cover estimates on several randomly selected reef segments (roughly 40 consecutive survey images) and compared against estimates by human experts. After verifying that the estimated covers were highly correlated with those by human experts we deployed the network on the whole set of collected imagery. Automated image annotation using this method is very fast; on average it only requires 0.2 seconds, three orders of magnitude faster than manual analysis. Analysis of hundred of thousands of images from a reef region can therefore be achieved in a manner of days. For example; over 190,000 survey quadrats from GBR were automatically annotated in one week using a single computational unit (a NVIDIA Titan X GPU).

Further methodological details can be found at:

González-Rivero M., O. Beijbom, A. Rodriguez-Ramirez, T. Holtrop, Y. González-Marrero, A. Ganase, Chris Roelfsema, S. Phinn and O. Hoegh-Guldberg. 2016. Scaling up Ecological Measurements of Coral Reefs Using Semi-Automated Field Image Collection and Analysis. Remote Sens. 8, 1:30; doi:10.3390/rs8010030.

González-Rivero M., P. Bongaerts, O. Beijbom, O. Pizarro, A. Friedman, A. Rodriguez-Ramirez, B. Upcroft, D. Laffoley, D. Kline, R. Vevers, and O. Hoegh-Guldberg. 2014. The Catlin Seaview Survey – kilometre-scale seascape assessment, and monitoring of coral reef ecosystems. Aquatic Conservation: Mar. Freshw. Ecosyst. 24(Supp. 2): 184-198

Beijbom O, Edmunds PJ, Roelfsema C, Smith J, Kline DI, Neal BP, et al. 2015. Towards Automated Annotation of Benthic Survey Images: Variability of Human Experts and Operational Modes of Automation. PLoS ONE 10(7): e0130312. doi:10.1371/journal.pone.0130312

Beijbom, O, P.J.Edmunds, D.I.Kline, B.G.Mitchell, D.Kriegman. 2012. Automated Annotation of Coral Reef Survey Images. IEEE Conference on Computer Vision (CVPR), Providence, Rhode Island, June 2012

Read our Science Papers