Examinando por Materia "Software"
Mostrando 1 - 2 de 2
Resultados por página
Opciones de ordenación
Publicación Acceso abierto NAIRA a tool to automatic mammals genera identification in camera trapping pictures(Universidad de Jena, 2018-09-24) Díaz-Pulido, Angélica; Isaza Narváez, Claudia; Pulido Castelblanco, LuisCamera traps are an efficient tool for detecting terrestrial mammals and birds. Vast amounts of presence data and information about distribution and size of mammals and birds have been generated in a very short time using this approach. The first step into a monitoring study, using camera trapping is to analyse the photographs. However, processing times, when it is done manually, can take longer because of the large amount of data collected. Pre-selecting relevant pictures using an automatic system and automatically identify the animals is an alternative to reduce the analysis time. The challenges to automatic identify the mammal´s genus from camera trap photos are: few examples of some genera (unbalanced classes problem), variation in light levels, constant changes in the scene, animal partially occluded, blurred photographs and other variations resulting from the natural dynamics of the ecosystem. Until now there has not been a computational tool to help in the specific task of labelling the animal´s genus. Thus, it is necessary to design new tools that automate the processing of these photographs.Publicación Acceso abierto NAIRA: a tool in the management and processing of camera trap images(Instituto de Investigación de Recursos Biológicos Alexander von Humboldt) Díaz-Pulido, Angélica; Pulido Castelblanco, Luis; Isaza Narváez, ClaudiaCamera traps are an efficient tool for detecting terrestrial mammals and birds. Vast amounts of presence data and information about distribution and size of mammals and birds have been generated in a very short time using this approach. However, processing times, when done manually, can take longer because of the large amount of data collected. The first step processing the data is to analyze the photographs. The sequences of images captured are complex due to constant changes in the scenes, variation in light levels, and different climatic conditions between triggers and other variations resulting from the natural dynamics of the ecosystem. The manual analysis of camera trap information is time-consuming and as a consequence, conservation oriented strategies based on data are generated slower than the speed of the changes occurring in the study areas. Thus, it is necessary to design new tools that automate the processing of these photographs. Here we introduce a new version of the software NAIRA. This software provides the user with tools for handling large quantities of camera trap images. NAIRA uses computational intelligence techniques to extract metadata, build databases, assist species labeling and automatically classify species captured in images using the photo-trapping technique. The photographs are classified into pictures with animals and without animals using a fuzzy classifier and a second classification distinguishes between birds and mammals using an Artificial Neural Network (ANN). Finally NAIRA identifies the taxonomic order in the detected mammals using Support Vector Machine (SVM) algorithms. With Naira scientists can process information in less time. The attendees will know in detail the functions of the software to recognize the advantages of the processing of this type of images with NAIRA.