1
|
Smith J, Wycherley A, Mulvaney J, Lennane N, Reynolds E, Monks CA, Evans T, Mooney T, Fancourt B. Man versus machine: cost and carbon emission savings of 4G-connected Artificial Intelligence technology for classifying species in camera trap images. Sci Rep 2024; 14:14530. [PMID: 38914636 PMCID: PMC11196731 DOI: 10.1038/s41598-024-65179-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Accepted: 06/18/2024] [Indexed: 06/26/2024] Open
Abstract
Timely and accurate detection and identification of species are crucial for monitoring wildlife for conservation and management. Technological advances, including connectivity of camera traps to mobile phone networks and artificial intelligence (AI) algorithms for automated species identification, can potentially improve the timeliness and accuracy of species detection and identification. Adoption of this new technology, however, is often seen as cost-prohibitive as it has been difficult to calculate the cost savings or qualitative benefits over the life of the program. We developed a decision tool to quantify potential cost savings associated with incorporating the use of mobile phone network connectivity and AI technologies into monitoring programs. Using a feral cat eradication program as a case study, we used our decision tool to quantify technology-related savings in costs and carbon emissions, and compared the accuracy of AI species identification to that of experienced human observers. Over the life of the program, AI technology yielded cost savings of $0.27 M and when coupled with mobile phone network connectivity, AI saved $2.15 M and 115,838 kg in carbon emissions, with AI algorithms outperforming human observers in both speed and accuracy. Our case study demonstrates how advanced technologies can improve accuracy and cost-effectiveness and improve monitoring program efficiencies.
Collapse
Affiliation(s)
- James Smith
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia.
- School of Agriculture and Environmental Science, University of Western Australia, Perth, WA, 6009, Australia.
- Bush Heritage Australia, Melbourne, VIC, 3008, Australia.
- School of Biology and Environmental Science, Queensland University of Technology, Brisbane, Australia.
| | - Ashleigh Wycherley
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
- Department of Environment and Water, Government of South Australia, Kingscote, Australia
| | - Josh Mulvaney
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
| | - Nathan Lennane
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
| | - Emily Reynolds
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
| | | | - Tom Evans
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
| | - Trish Mooney
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
| | - Bronwyn Fancourt
- Kangaroo Island Landscape Board, Kingscote, SA, 5223, Australia
- School of Environmental and Rural Science, University of New England, Armidale, NSW, 2351, Australia
- Department of Environment, Science and Innovation, Queensland Parks and Wildlife Service & Partnerships, Toowoomba, Australia
| |
Collapse
|
2
|
Schütz AK, Louton H, Fischer M, Probst C, Gethmann JM, Conraths FJ, Homeier-Bachmann T. Automated Detection and Counting of Wild Boar in Camera Trap Images. Animals (Basel) 2024; 14:1408. [PMID: 38791626 PMCID: PMC11117377 DOI: 10.3390/ani14101408] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2024] [Revised: 04/30/2024] [Accepted: 05/02/2024] [Indexed: 05/26/2024] Open
Abstract
Camera traps are becoming widely used for wildlife monitoring and management. However, manual analysis of the resulting image sets is labor-intensive, time-consuming and costly. This study shows that automated computer vision techniques can be extremely helpful in this regard, as they can rapidly and automatically extract valuable information from the images. Specific training with a set of 1600 images obtained from a study where wild animals approaching wild boar carcasses were monitored enabled the model to detect five different classes of animals automatically in their natural environment with a mean average precision of 98.11%, namely 'wild boar', 'fox', 'raccoon dog', 'deer' and 'bird'. In addition, sequences of images were automatically analyzed and the number of wild boar visits and respective group sizes were determined. This study may help to improve and speed up the monitoring of the potential spread of African swine fever virus in areas where wild boar are affected.
Collapse
Affiliation(s)
- Anne K. Schütz
- Institute of Epidemiology, Friedrich-Loeffler-Institut, Federal Research Institute for Animal Health, Südufer 10, 17493 Greifswald-Insel Riems, Germany; (C.P.); (J.M.G.); (F.J.C.); (T.H.-B.)
| | - Helen Louton
- Animal Health and Animal Welfare, Faculty of Agricultural and Environmental Science, University of Rostock, Justus-von-Liebig-Weg 6, 18059 Rostock, Germany;
| | - Mareike Fischer
- Institute of Mathematics and Computer Science, University of Greifswald, Walther-Rathenau-Straße 47, 17487 Greifswald, Germany;
| | - Carolina Probst
- Institute of Epidemiology, Friedrich-Loeffler-Institut, Federal Research Institute for Animal Health, Südufer 10, 17493 Greifswald-Insel Riems, Germany; (C.P.); (J.M.G.); (F.J.C.); (T.H.-B.)
- Federal Ministry for Economic Cooperation and Development, Stresemannstraße 94, 10963 Bonn, Germany
| | - Jörn M. Gethmann
- Institute of Epidemiology, Friedrich-Loeffler-Institut, Federal Research Institute for Animal Health, Südufer 10, 17493 Greifswald-Insel Riems, Germany; (C.P.); (J.M.G.); (F.J.C.); (T.H.-B.)
| | - Franz J. Conraths
- Institute of Epidemiology, Friedrich-Loeffler-Institut, Federal Research Institute for Animal Health, Südufer 10, 17493 Greifswald-Insel Riems, Germany; (C.P.); (J.M.G.); (F.J.C.); (T.H.-B.)
| | - Timo Homeier-Bachmann
- Institute of Epidemiology, Friedrich-Loeffler-Institut, Federal Research Institute for Animal Health, Südufer 10, 17493 Greifswald-Insel Riems, Germany; (C.P.); (J.M.G.); (F.J.C.); (T.H.-B.)
| |
Collapse
|
3
|
Haswell PM, López-Pérez AM, Clifford DL, Foley JE. Recovering an endangered vole and its habitat may help control invasive house mice. FOOD WEBS 2022. [DOI: 10.1016/j.fooweb.2022.e00267] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
|
4
|
Diggins CA, Lipford A, Farwell T, Eline DV, Larose SH, Kelly CA, Clucas B. Can camera traps be used to differentiate species of North American flying squirrels? WILDLIFE SOC B 2022. [DOI: 10.1002/wsb.1323] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Affiliation(s)
- Corinne A. Diggins
- Department of Fish and Wildlife Conservation Virginia Tech Blacksburg VA 24061 USA
| | - Aylett Lipford
- School of Renewable Natural Resources Louisiana State University Baton Rouge LA 70808 USA
| | - Travis Farwell
- Department of Wildlife Humboldt State University Arcata CA 95521 USA
| | - Drew V. Eline
- Department of Environmental and Forest Biology SUNY College of Environmental Science and Forestry Syracuse NY 13210 USA
| | - Summer H. Larose
- School of Natural Resources University of Missouri Columbia MO 65211 USA
| | | | - Barbara Clucas
- Department of Wildlife Humboldt State University Arcata CA 95521 USA
| |
Collapse
|
5
|
Gracanin A, Mikac KM. Camera traps reveal overlap and seasonal variation in the diel activity of arboreal and semi-arboreal mammals. Mamm Biol 2022. [DOI: 10.1007/s42991-021-00218-y] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
AbstractOur study aimed to investigate seasonal variation in the activity of arboreal and semi-arboreal mammals and investigate their overlap in temporal activity, as well temporal shifts in activity because of behavioural interference. In our camera trapping study in a fragmented landscape in south-eastern Australia, a total of ten arboreal and semi-arboreal species were found, with 35,671 independent observations recorded over 6517 camera trap nights. All species were found to be nocturnal; however, a notable number of daytime observations were made for several species (i.e. brown antechinus, Antechinus stuartii; sugar glider, Petaurus breviceps; bush rat, Rattus fuscipes; brown rat, Rattus norvegicus). Seasonal variations in diel activity were observed through an increase in crepuscular activity in spring and summer for antechinus, sugar gliders, brown rats, brushtail possums, Trichosurus vulpecula and ringtail possums, Pseudocheirus peregrinus. Diel activity overlap between species was high, that is 26/28 species comparisons had overlap coefficients (Δ) > 0.75. The species pair with the least amount of overlap was between southern bobucks, Trichosurus cunninghami and brown antechinus (Δ4 = 0.66). The species pair with the most overlap was between the native sugar glider and introduced brown rat (Δ4 = 0.93). When comparing the activity of sugar gliders in sites with low and high abundance of brown rats, sugar gliders appear to shift their activity relative to the brown rats. Similarly, behavioural interference was also observed between antechinus and sugar gliders, and when comparing sites of low and high abundance of sugar glider, antechinus had a shift in activity. Our work provides some of the first quantification of temporal patterns for several of the species in this study, and the first for a community of arboreal and semi-arboreal mammals. Our results indicate that some shifts in behaviour are potentially occurring in response to behavioural interference, allowing for coexistence by means of temporal partitioning.
Collapse
|
6
|
|
7
|
Coulson G, Snape MA, Cripps JK. How many macropods?
A manager’s guide to small‐scale population surveys of kangaroos and wallabies. ECOLOGICAL MANAGEMENT & RESTORATION 2021. [DOI: 10.1111/emr.12485] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/17/2023]
|
8
|
Gadsden GI, Malhotra R, Schell J, Carey T, Harris NC. Michigan ZoomIN: Validating Crowd‐Sourcing to Identify Mammals from Camera Surveys. WILDLIFE SOC B 2021. [DOI: 10.1002/wsb.1175] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Affiliation(s)
- Gabriel I. Gadsden
- 1105 N. University Ave., Applied Wildlife Ecology Lab, Ecology and Evolutionary Biology University of Michigan Ann Arbor MI 48109 USA
| | - Rumaan Malhotra
- Shapiro Design Lab University of Michigan Ann Arbor MI 48109 USA
| | - Justin Schell
- Shapiro Design Lab University of Michigan Ann Arbor MI 48109 USA
| | - Tiffany Carey
- 1105 N. University Ave., Applied Wildlife Ecology Lab, Ecology and Evolutionary Biology University of Michigan Ann Arbor MI 48109 USA
| | - Nyeema C. Harris
- 1105 N. University Ave., Applied Wildlife Ecology Lab, Ecology and Evolutionary Biology University of Michigan Ann Arbor MI 48109 USA
| |
Collapse
|
9
|
Potter TI, Greenville AC, Dickman CR. Night of the hunter: using cameras to quantify nocturnal activity in desert spiders. PeerJ 2021; 9:e10684. [PMID: 33585081 PMCID: PMC7860110 DOI: 10.7717/peerj.10684] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/03/2020] [Accepted: 12/10/2020] [Indexed: 11/20/2022] Open
Abstract
Invertebrates dominate the animal world in terms of abundance, diversity and biomass, and play critical roles in maintaining ecosystem function. Despite their obvious importance, disproportionate research attention remains focused on vertebrates, with knowledge and understanding of invertebrate ecology still lacking. Due to their inherent advantages, usage of camera traps in ecology has risen dramatically over the last three decades, especially for research on mammals. However, few studies have used cameras to reliably detect fauna such as invertebrates or used cameras to examine specific aspects of invertebrate ecology. Previous research investigating the interaction between wolf spiders (Lycosidae: Lycosa spp.) and the lesser hairy-footed dunnart (Sminthopsis youngsoni) found that camera traps provide a viable method for examining temporal activity patterns and interactions between these species. Here, we re-examine lycosid activity to determine whether these patterns vary with different environmental conditions, specifically between burned and unburned habitats and the crests and bases of sand dunes, and whether cameras are able to detect other invertebrate fauna. Twenty-four cameras were deployed over a 3-month period in an arid region in central Australia, capturing 2,356 confirmed images of seven invertebrate taxa, including 155 time-lapse images of lycosids. Overall, there was no clear difference in temporal activity with respect to dune position or fire history, but twice as many lycosids were detected in unburned compared to burned areas. Despite some limitations, camera traps appear to have considerable utility as a tool for determining the diel activity patterns and habitat use of larger arthropods such as wolf spiders, and we recommend greater uptake in their usage in future.
Collapse
Affiliation(s)
- Tamara I Potter
- Terrestrial Ecosystem Research Network, School of Biological Sciences, University of Adelaide, Adelaide, South Australia, Australia.,Desert Ecology Research Group, School of Life and Environmental Sciences, University of Sydney, Sydney, New South Wales, Australia
| | - Aaron C Greenville
- Desert Ecology Research Group, School of Life and Environmental Sciences, University of Sydney, Sydney, New South Wales, Australia.,National Environmental Science Program Threatened Species Recovery Hub, School of Life and Environmental Sciences, University of Sydney, Sydney, New South Wales, Australia
| | - Christopher R Dickman
- Desert Ecology Research Group, School of Life and Environmental Sciences, University of Sydney, Sydney, New South Wales, Australia.,National Environmental Science Program Threatened Species Recovery Hub, School of Life and Environmental Sciences, University of Sydney, Sydney, New South Wales, Australia
| |
Collapse
|
10
|
Kays R, McShea WJ, Wikelski M. Born‐digital biodiversity data: Millions and billions. DIVERS DISTRIB 2020. [DOI: 10.1111/ddi.12993] [Citation(s) in RCA: 34] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022] Open
Affiliation(s)
- Roland Kays
- North Carolina Museum of Natural Sciences and North Carolina State University Raleigh NC USA
| | | | - Martin Wikelski
- Department of Migration Max Planck Institute of Animal Behavior Radolfzell Germany
- Centre for the Advanced Study of Collective Behaviour University of Konstanz Radolfzell Germany
| |
Collapse
|