Animal Identification in Low Quality Camera-Trap Images Using Very Deep Convolutional Neural Networks and Confidence Thresholds

Monitoring animals in the wild without disturbing them is possible using camera trapping framework. Automatic triggered cameras, which take a burst of images of animals in their habitat, produce great volumes of data, but often result in low image quality. This high volume data must be classified by a human expert. In this work a two step classification is proposed to get closer to an automatic and trustfully camera-trap classification system in low quality images. Very deep convolutional neural networks were used to distinguish images, firstly between birds and mammals, secondly between mammals sets. The method reached \(97.5\%\) and \(90.35\%\) in each task. An alleviation mode using a confidence threshold of automatic classification is proposed, allowing the system to reach \(100\%\) of performance traded with human work.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Chaitanya K. Baru,et al.  Data acquisition and management software for camera trap data: A case study from the TEAM Network , 2011, Ecol. Informatics.

[4]  Jiangping Wang,et al.  Automated identification of animal species in camera trap images , 2013, EURASIP J. Image Video Process..

[5]  Jesús Francisco Vargas-Bonilla,et al.  Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks , 2016, Ecol. Informatics.

[6]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[7]  A. F. O'connell,et al.  Camera traps in animal ecology : methods and analyses , 2011 .

[8]  David D. Lewis,et al.  Heterogeneous Uncertainty Sampling for Supervised Learning , 1994, ICML.

[9]  Chris Roelfsema,et al.  Towards Automated Annotation of Benthic Survey Images: Variability of Human Experts and Operational Modes of Automation , 2015, PloS one.

[10]  Laura Igual,et al.  Robust gait-based gender classification using depth cameras , 2013, EURASIP Journal on Image and Video Processing.

[11]  Tony X. Han,et al.  Deep convolutional neural network based species recognition for wild animal monitoring , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[14]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).