CrowdPet: deep learning applied to the detection of dogs in the wild

XXV Congresso de Iniciação Científica da Unicamp, Campinas, SP, Brazil, 2017

Abstract

Biometry is the statistical study of physical or behavioral characteristics of living beings, mainly applied to the identification of individuals. Visual biometric methods map images to identities, and have been applied almost exclusively to humans. However, animal visual biometry is significantly different than that of humans, and current methods cannot be used interchangeably. The CrowdPet initiative studies and proposes methods to the problem of animal biometric identification, in order to identify and generate analytics related to stray animals. As part of this effort, in this work we present a method for detecting dogs in images, despite changes in pose and illumination, using Deep Learning. Experiments show promising results, in terms of accuracy, using challenging current datasets.

BibTeX

@inproceedings{capone17cicunicamp,
    authors      = “Victor Capone and Carlos Figueiredo and Eduardo Valle and Fernanda A. Andal{\‘o}“,
    title        = “CrowdPet: deep learning applied to the detection of dogs in the wild”,
    booktitle    = “XXV Congresso de Iniciação Científica da Unicamp”,
    year         = 2017,
    address      = “Campinas, SP, Brazil”,
    note         = “short paper”,
}