1
|
Penteriani V, Hartasánchez A, García JD, Magadan Ruitiña JR, Mar Delgado MD. Brown bear body patches are temporally stable and represent a unique individual visual signature. URSUS 2023. [DOI: 10.2192/ursus-d-22-00015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/25/2023]
Affiliation(s)
- Vincenzo Penteriani
- National Museum of Natural Sciences (MNCN), Department of Evolutionary Ecology, Spanish National Research Council (CSIC), c/José Gutiérrez Abascal 2, 28006 Madrid, Spain
| | - Alfonso Hartasánchez
- FAPAS Fondo para la Protección de los Animales Salvajes, Ctra. AS-228, km 8.9 – Tuñón, 33115 Santo Adriano, Asturias, Spain
| | - Juan Díaz García
- Consejería de Ordenación del Territorio, Infraestructuras y Medio Ambiente, Dirección General de Biodiversidad, Principado de Asturias, 33000 Oviedo, Spain
| | - José Ramón Magadan Ruitiña
- FAPAS Fondo para la Protección de los Animales Salvajes, Ctra. AS-228, km 8.9 – Tuñón, 33115 Santo Adriano, Asturias, Spain
| | - María del Mar Delgado
- Biodiversity Research Institute (IMIB, CSIC-UO-PA), Mieres Campus, 33600 Mieres, Spain
| |
Collapse
|
2
|
Multispecies facial detection for individual identification of wildlife: a case study across ursids. Mamm Biol 2022; 102:921-933. [PMID: 36164481 PMCID: PMC9499902 DOI: 10.1007/s42991-021-00168-5] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2021] [Accepted: 08/06/2021] [Indexed: 01/31/2023]
Abstract
To address biodiversity decline in the era of big data, replicable methods of data processing are needed. Automated methods of individual identification (ID) via computer vision are valuable in conservation research and wildlife management. Rapid and systematic methods of image processing and analysis are fundamental to an ever-growing need for effective conservation research and practice. Bears (ursids) are an interesting test system for examining computer vision techniques for wildlife, as they have variable facial morphology, variable presence of individual markings, and are challenging to research and monitor. We leveraged existing imagery of bears living under human care to develop a multispecies bear face detector, a critical part of individual ID pipelines. We compared its performance across species and on a pre-existing wild brown bear Ursus arctos dataset (BearID), to examine the robustness of convolutional neural networks trained on animals under human care. Using the multispecies bear face detector and retrained sub-applications of BearID, we prototyped an end-to-end individual ID pipeline for the declining Andean bear Tremarctos ornatus. Our multispecies face detector had an average precision of 0.91-1.00 across all eight bear species, was transferable to images of wild brown bears (AP = 0.93), and correctly identified individual Andean bears in 86% of test images. These preliminary results indicate that a multispecies-trained network can detect faces of a single species sufficiently to achieve high-performance individual classification, which could speed-up the transferability and application of automated individual ID to a wider range of taxa. Supplementary Information The online version contains supplementary material available at 10.1007/s42991-021-00168-5.
Collapse
|
3
|
Penteriani V, González-Bernardo E, Hartasánchez A, Ruiz-Villar H, Morales-González A, Ordiz A, Bombieri G, Diaz García J, Cañedo D, Bettega C, Delgado MDM. Visual marking in mammals first proved by manipulations of brown bear tree debarking. Sci Rep 2021; 11:9492. [PMID: 33947891 PMCID: PMC8096968 DOI: 10.1038/s41598-021-88472-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2021] [Accepted: 04/05/2021] [Indexed: 11/08/2022] Open
Abstract
The rather limited human ability to understand animal vision and visual signalling has frequently clouded our expectations concerning the visual abilities of other animals. But there are multiple reasons to suspect that visual signalling is more widely employed by animals than previously thought. Because visibility of visual marks depends on the background in which they are seen, species spending most of their time living in dark conditions (e.g., in forests and/or having crepuscular and nocturnal habits) may rely on bright signals to enhance visual display. Here, as a result of experimental manipulations, we present, for the first time ever, evidence supporting the use of a new channel of intraspecific communication by a mammal species, i.e., brown bear Ursus arctos adult males relying on visual marks during mating. Bear reactions to our manipulation suggest that visual signalling could represent a widely overlooked mechanism in mammal communication, which may be more broadly employed than was previously thought.
Collapse
Affiliation(s)
- Vincenzo Penteriani
- Research Unit of Biodiversity (UMIB, CSIC-UO-PA), Mieres Campus, 33600, Mieres, Spain.
| | - Enrique González-Bernardo
- Research Unit of Biodiversity (UMIB, CSIC-UO-PA), Mieres Campus, 33600, Mieres, Spain
- Pyrenean Institute of Ecology (IPE), C.S.I.C., Avda. Montañana 1005, 50059, Zaragoza, Spain
| | - Alfonso Hartasánchez
- FAPAS Fondo para la Protección de los Animales Salvajes, Ctra. AS-228, km 8,9 - Tuñón, 33115, Santo Adriano, Asturias, Spain
| | - Héctor Ruiz-Villar
- Research Unit of Biodiversity (UMIB, CSIC-UO-PA), Mieres Campus, 33600, Mieres, Spain
| | - Ana Morales-González
- Department of Conservation Biology, Estación Biológica de Doñana, C.S.I.C, Avda. Americo Vespucio 26, 41092, Sevilla, Spain
| | - Andrés Ordiz
- Faculty of Environmental Sciences and Natural Resource Management, Norwegian University of Life Sciences, Postbox 5003, NO-1432, Ås, Norway
| | - Giulia Bombieri
- MUSE - Museo delle Scienze, Sezione Zoologia dei Vertebrati, Corso del Lavoro e della Scienza 3, 38123, Trento, Italy
| | - Juan Diaz García
- Consejería de Ordenación del Territorio, Infraestructuras y Medio Ambiente, Dirección General de Biodiversidad, Oviedo, Principado de Asturias, Spain
| | - David Cañedo
- Consejería de Ordenación del Territorio, Infraestructuras y Medio Ambiente, Dirección General de Biodiversidad, Oviedo, Principado de Asturias, Spain
| | - Chiara Bettega
- Research Unit of Biodiversity (UMIB, CSIC-UO-PA), Mieres Campus, 33600, Mieres, Spain
| | - María Del Mar Delgado
- Research Unit of Biodiversity (UMIB, CSIC-UO-PA), Mieres Campus, 33600, Mieres, Spain
| |
Collapse
|