Mobile mapping system (MMS2) for detecting roadkills.

Ribeiro, H., Sillero, N. y Guedes, D. Mobile mapping system (MMS2) for detecting roadkills. 2020 IENE International Conference. Abstract book. Évora: Infrastructure & Ecology Network Europe. 2021, Vol. 4.1.2, Num. 3, pag. 73. ISSN 978-972-778-182-9

Roads affect negatively wildlife, from direct mortality to habitat fragmentation. Mortality caused by collision with vehicles on roads is a major threat to many species. Monitoring animal road-kills is essential to stablish correct road mitigation measures. Many countries have national monitoring systems for identifying mortality hotspots. We present here an improved version of the mobile mapping system (MMS2) for detecting Roadkills not only for amphibians but small birds as well. It is composed by two stereo multi-spectral and high definition camera (ZED), a high-power processing laptop, a GPS device connected to the laptop, and a small support device attachable to the back of any vehicle. The system is controlled by several applications that manage all the video recording steps as well as the GPS acquisition, merging everything in a single final file, ready to be examine by an algorithm at posterior. We used the state-of-the-art machine learning computer vision algorithm (CNN: Convolutional Neural Network) to automatically detect animals on roads. This self-learning algorithm needs a large number of images with alive animals, road-killed animals and any objects likely to be found on roads (e.g. garbage thrown away by drivers) in order to be trained. The greater the image database, the greater the detection efficiency. This improved version of the mobile mapping system presents very good results. The algorithm has a good effectiveness in detecting small birds and amphibians.

Datos y Recursos

Metadatos
Descargar
DCAT-AP/NTI-RISP

Información básica
Tipo de recurso Texto
Fecha de creación 17-09-2024
Fecha de última modificación 17-09-2024
Mostrar histórico de cambios
Identificador de los metadatos 61eef668-6f2d-562b-89b5-e0f33883583e
Idioma de los metadatos Español
Temáticas (NTI-RISP)
Categoría del conjunto de alto valor (HVD)
Categoría temática ISO 19115 biota
Identificador alternativo
URI de palabras clave
Codificación UTF-8
Información espacial
Identificador INSPIRE ESPMITECOIEPNBFRAGM707
Temas INSPIRE
Identificador geográfico España
Sistema de Referencia de Coordenadas
Tipo de representación espacial
Extensión espacial
"{\"type\": \"Polygon\", \"coordinates\": [[[-18.16, 27.64], [4.32, 27.64], [4.32, 43.79], [-18.16, 43.79], [-18.16, 27.64]]]}"
Resolución espacial del dataset (m)
Procedencia
Declaración de linaje
Perfil de Metadatos
Conformidad
Conjunto de datos de origen
Frecuencia de actualización
Fuentes
  1. 2020 IENE International Conference. Abstract book. Vol. 4.1.2
  2. Num. 3
  3. pag. 73
Propósito
Pasos del proceso
Cobertura temporal (Inicio)
Cobertura temporal (Fin)
Notas sobre la versión
Versión
Vigencia del conjunto de datos
Parte responsable
Nombre del autor Ribeiro, H., Sillero, N. y Guedes, D.
Nombre del mantenedor
Identificador del autor
Email del autor
Web del autor
Identificador del mantenedor
Email del mantenedor
Web del mantenedor