A computer vision approach for studying fossorial and cryptic crabs

Despite the increasing need to catalogue and describe biodiversity and the ecosystem processes it underpins, these tasks remain inherently challenging. This is particularly true for species that are difficult to observe in their natural environment, such as fossorial and cryptic crabs that inhabit intertidal sediments. Traditional sampling techniques for intertidal crabs are often invasive, labour intensive and/or inconsistent. These factors can limit the amount and type of data that can be collected which in turn hinders our ability to obtain reliable ecological estimates and compare findings between studies. Computer vision and machine learning algorithms present an opportunity to innovate and improve sampling approaches. Moreover, cheaper and tougher recording devices and the diversity of open source software further boost the possibilities of achieving rigorous image-based sampling, which can broaden the range of questions that can be addressed from the data collected. Despite its significant potential, the software and algorithms associated with image-based sampling may be daunting to researchers without expertise in computer vision. Therefore, there is a need to develop protocols and data processing workflows to showcase the value of embracing new technologies. This paper presents a non-invasive computer vision and learning protocol for sampling fossorial and cryptic crabs in their natural environment. The image-based protocol is underpinned by fit-for-purpose and off-the-shelf software. We demonstrate this approach using fiddler crab and sediment recordings to study and quantify crab abundance, motion patterns, behaviour, intraspecific interactions, and estimate bioturbation rates. We discuss current limitations in this protocol and identify opportunities for improvement and additional data stream options that can be obtained from this approach. We conclude that this protocol can overcome some of the limitations associated with traditional techniques for sampling intertidal crabs, and could be applied to other taxa or ecosystems that present similar challenges. We believe this sampling and analytical framework represents an important step forward in understanding the ecology of species and their functional role within ecosystems.

[1]  M. Salmon On the Reproductive Behavior of the Fiddler Crab Uca thayeri, with Comparisons to U. pugilator and U. vocans: Evidence for Behavioral Convergence , 1987 .

[2]  E. Revilla,et al.  A movement ecology paradigm for unifying organismal movement research , 2008, Proceedings of the National Academy of Sciences.

[3]  N. Smith,et al.  Fiddler crab burrowing affects growth and production of the white mangrove (Laguncularia racemosa) in a restored Florida coastal marsh , 2009 .

[4]  Marc Chaumont,et al.  A Deep learning method for accurate and fast identification of coral reef fishes in underwater images , 2018, Ecol. Informatics.

[5]  Rui F. Oliveira,et al.  Comparison of non-invasive methods for quantifying population density of the fiddler crab Uca tangeri , 2003, Journal of the Marine Biological Association of the United Kingdom.

[6]  E. Kristensen Mangrove crabs as ecosystem engineers; with emphasis on sediment processes , 2008 .

[7]  W. R. Rhodes Fiddler crabs of the world, ocypodidae: Genus Uca By Jocelyn Crane. Princeton University Press (1975). Pp. xxiii + 736. $75 , 1978, Animal Behaviour.

[8]  Lian Pin Koh,et al.  Futurecasting ecological research: The rise of technoecology , 2018 .

[9]  M. Sheaves,et al.  Short-circuit in the mangrove food chain , 2000 .

[10]  Y. Kurihara,et al.  The effects of burrowing of Helice tridens (De Haan) on the soil of a salt-marsh habitat , 1987 .

[11]  Marc Olano,et al.  Optimal Altitude, Overlap, and Weather Conditions for Computer Vision UAV Estimates of Forest Structure , 2015, Remote. Sens..

[12]  Boaz Zion,et al.  Review: The use of computer vision technologies in aquaculture - A review , 2012 .

[13]  M. Salmon The courtship, aggression and mating system of a “primitive” fiddler crab (Uca vocans: Ocypodidae) , 1984 .

[14]  Borko Furht,et al.  Neural Network Approach to Background Modeling for Video Object Segmentation , 2007, IEEE Transactions on Neural Networks.

[15]  Matthew B Jones,et al.  Ecoinformatics: supporting ecology as a data-intensive science. , 2012, Trends in ecology & evolution.

[16]  Simone Marini,et al.  Underwater Fish Detection with Weak Multi-Domain Supervision , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[17]  Euan S. Harvey,et al.  Direct sensing of the size frequency and abundance of target and non-target fauna in Australian fisheries - a national workshop, 4-7 September 2000, Rottnest Island, Western Australia , 2001 .

[18]  Jarrett E. K. Byrnes,et al.  Marine biodiversity and ecosystem functioning: what’s known and what’s next? , 2015 .

[19]  W. Ripple,et al.  World Scientists’ Warning to Humanity: A Second Notice , 2017 .

[20]  Boris Jutzi,et al.  Semantic 3D scene interpretation: A framework combining optimal neighborhood size selection with relevant features , 2014 .

[21]  K. Diele,et al.  Activity patterns, feeding and burrowing behaviour of the crab Ucides cordatus (Ucididae) in a high intertidal mangrove forest in North Brazil. , 2009 .

[22]  Hervé Glotin,et al.  Fine-grained object recognition in underwater visual data , 2016, Multimedia Tools and Applications.

[23]  R. Kastner,et al.  Automated Techniques for Detection and Recognition of Fishes using Computer Vision Algorithms , 2012 .

[24]  J. Levinton,et al.  Molecular phylogeny analysis of fiddler crabs: test of the hypothesis of increasing behavioral complexity in evolution. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[25]  B. Cardinale Impacts of Biodiversity Loss , 2012, Science.

[26]  Rachel K. Gittman,et al.  Fiddler crabs facilitate Spartina alterniflora growth, mitigating periwinkle overgrazing of marsh habitat. , 2013, Ecology.

[27]  Clément Calenge,et al.  The package “adehabitat” for the R software: A tool for the analysis of space and habitat use by animals , 2006 .

[28]  Stefan B. Williams,et al.  Characterization of measurement errors using structure‐from‐motion and photogrammetry to measure marine habitat structural complexity , 2017, Ecology and evolution.

[29]  Ben. G. Weinstein A computer vision for animal ecology. , 2018, The Journal of animal ecology.

[30]  B. Eyre,et al.  The effect of natural populations of the burrowing and grazing soldier crab (Mictyris longicarpus) on sediment irrigation, benthic metabolism and nitrogen fluxes , 2004 .

[31]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[32]  Steven V. Viscido,et al.  Quantitative analysis of fiddler crab flock movement: evidence for ‘selfish herd’ behaviour , 2002, Animal Behaviour.

[33]  L. C. Katz Effects of burrowing by the fiddler crab, Uca pugnax (Smith) , 1980 .

[34]  Judea Pearl,et al.  Direct and Indirect Effects , 2001, UAI.

[35]  D. Holdstock Past, present--and future? , 2005, Medicine, conflict, and survival.

[36]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[37]  Derek Hoiem,et al.  Single-image shadow detection and removal using paired regions , 2011, CVPR 2011.

[38]  Severino G. Salmo,et al.  The Loss of Species: Mangrove Extinction Risk and Geographic Areas of Global Concern , 2010, PloS one.

[39]  J. Leon,et al.  Estimating animal populations and body sizes from burrows: marine ecologists have their heads buried in the sand , 2016 .

[40]  K. McGuinness,et al.  Developing methods for quantifying the apparent abundance of fiddler crabs (Ocypodidae: Uca) in mangrove habitats , 1999 .

[41]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[42]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[43]  E. Fanjul,et al.  Impact of crab bioturbation on benthic flux and nitrogen dynamics of Southwest Atlantic intertidal marshes and mudflats , 2011 .

[44]  Fonseca,et al.  Population dynamics, spatial dispersion and somatic growth of the sand fiddler crab ilea pugilator , 1984 .

[45]  M. Rosenberg THE SYSTEMATICS AND TAXONOMY OF FIDDLER CRABS: A PHYLOGENY OF THE GENUS UCA , 2001 .

[46]  Gábor Csárdi,et al.  The igraph software package for complex network research , 2006 .

[47]  J. Levinton,et al.  Molecular data and biogeography: Resolution of a controversy over evolutionary history of a pan-tropical group of invertebrates , 1996 .

[48]  P. Groffman,et al.  The Contribution of Crab Burrow Excavation to Carbon Availability in Surficial Salt-marsh Sediments , 2006, Ecosystems.

[49]  Christopher J. A. Macleod,et al.  Structure from motion photogrammetry in ecology: Does the choice of software matter? , 2019, Ecology and evolution.

[50]  Mubarak Shah,et al.  Automatic Tracking of Escherichia Coli Bacteria , 2008, MICCAI.

[51]  J. Zeil,et al.  The variable colours of the fiddler crab Uca vomeris and their relation to background and predation , 2006, Journal of Experimental Biology.

[52]  K. McGuinness,et al.  A Comparison of Methods for Estimating Relative Abundance of Grapsid Crabs , 2006, Wetlands Ecology and Management.

[53]  Xiu Li,et al.  Fast accurate fish detection and recognition of underwater images with Fast R-CNN , 2015, OCEANS 2015 - MTS/IEEE Washington.

[54]  M. Salmon,et al.  Spatial and temporal aspects of reproduction in North Carolina fiddler crabs (Uca pugilator Bosc) , 1983 .

[55]  Shing Yip Lee Ecological role of grapsid crabs in mangrove ecosystems: a review , 1998 .

[56]  C. Marshall,et al.  Has the Earth’s sixth mass extinction already arrived? , 2011, Nature.

[57]  Yang Song,et al.  The iNaturalist Species Classification and Detection Dataset , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[58]  B. Beinlich,et al.  Materials for a more stable subdivision of the genus Uca Leach , 2006 .

[59]  Phil F. Culverhouse,et al.  Automated identification of benthic epifauna with computer vision , 2019, Marine Ecology Progress Series.

[60]  Li Ma,et al.  Shadow removal with background difference method based on shadow position and edges attributes , 2012, EURASIP J. Image Video Process..

[61]  William K. Michener,et al.  Meta-information concepts for ecological data management , 2006, Ecol. Informatics.

[62]  John Reidar Mathiassen,et al.  Trends in application of imaging technologies to inspection of fish and fish products , 2011 .

[63]  Suneeta Agarwal,et al.  An Efficient Hierarchical Approach for Background Subtraction and Shadow Removal using Adaptive GMM and Color Discrimination , 2013 .

[64]  Fumio Takeshita Color changes of fiddler crab between seasons and under stressful conditions: Patterns of changes in lightness differ between carapace and claw , 2019, Journal of Experimental Marine Biology and Ecology.

[65]  Antonio Mauro Saraiva,et al.  A conceptual framework for quality assessment and management of biodiversity data , 2017, PloS one.

[66]  Changchang Wu,et al.  Towards Linear-Time Incremental Structure from Motion , 2013, 2013 International Conference on 3D Vision.

[67]  T. M. Costa,et al.  Potential effect of fiddler crabs on organic matter distribution: A combined laboratory and field experimental approach , 2017 .

[68]  François Michonneau,et al.  Ten Simple Rules for Digital Data Storage , 2016, PeerJ Prepr..

[69]  J. Kostka,et al.  Impact of fiddler crabs and plant roots on sediment biogeochemistry in a Georgia saltmarsh , 2003 .

[70]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[71]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[72]  Graham W. Taylor,et al.  Past, present and future approaches using computer vision for animal re‐identification from camera trap data , 2018, Methods in Ecology and Evolution.

[73]  S. Cannicci,et al.  Quantifying the density of mangrove crabs: Ocypodidae and Grapsidae , 2002 .

[74]  M. Bertness,et al.  Bioturbation of Burrowing Crabs Promotes Sediment Turnover and Carbon and Nitrogen Movements in an Estuarine Salt Marsh , 2010, Ecosystems.

[75]  T. Meziane,et al.  Role of grapsid crabs, Parasesarma erythrodactyla, in entry of mangrove leaves into an estuarine food web: a mesocosm study , 2009 .

[76]  Emmanuelle Gouillart,et al.  scikit-image: image processing in Python , 2014, PeerJ.

[77]  Jan Dirk Wegner,et al.  Contour Detection in Unstructured 3D Point Clouds , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[78]  D. Daffonchio,et al.  Fiddler crab bioturbation determines consistent changes in bacterial communities across contrasting environmental conditions , 2019, Scientific Reports.

[79]  Wes McKinney,et al.  Data Structures for Statistical Computing in Python , 2010, SciPy.

[80]  A. Robertson,et al.  The influence of crabs on litter processing in high intertidal mangrove forests in tropical Australia , 2004, Oecologia.

[81]  G. Perillo,et al.  Direct and indirect effects of burrowing crab Chasmagnathus granulatus activities on erosion of southwest Atlantic Sarcocornia‐dominated marshes , 2007 .

[82]  M. Skov,et al.  Comparative suitability of binocular observation, burrow counting and excavation for the quantification of the mangrove fiddler crab Uca annulipes (H. Milne Edwards) , 2001, Hydrobiologia.

[83]  E. Fanjul,et al.  Effect of crab bioturbation on organic matter processing in South West Atlantic intertidal sediments , 2015 .

[84]  M. Rosenberg Contextual Cross-Referencing of Species Names for Fiddler Crabs (Genus Uca): An Experiment in Cyber-Taxonomy , 2014, PloS one.

[85]  D. Felder,et al.  Burrow distributions and population estimates for the fiddler crabsUca spinicarpa andUca longisignalis in a Gulf of Mexico salt marsh , 1996 .

[86]  Richard Szeliski,et al.  Towards Internet-scale multi-view stereo , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[87]  L. Reaney,et al.  Foraging and mating opportunities influence refuge use in the fiddler crab, Uca mjoebergi , 2007, Animal Behaviour.

[88]  Vivek Hari Sridhar,et al.  Tracktor: image-based automated tracking of animal movement and behaviour , 2018, bioRxiv.

[89]  Pietro Perona,et al.  Automated image-based tracking and its application in ecology. , 2014, Trends in ecology & evolution.

[90]  J. Zieman,et al.  Fiddler crab (Uca spp.) burrows have little effect on surrounding sediment oxygen concentrations , 2013 .

[91]  José Nestor de Paula,et al.  Estimating the size of "Uca tangeri" (Crustacea: Ocypodidae) without massive crab capture , 2000 .

[92]  Phil F. Culverhouse,et al.  Fish identification from videos captured in uncontrolled underwater environments , 2016 .