Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks

@article{GomezVilla2017TowardsAW,
  title={Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks},
  author={Alex Gomez-Villa and Augusto Salazar and Jes{\'u}s Francisco Vargas-Bonilla},
  journal={ArXiv},
  year={2017},
  volume={abs/1603.06169}
}

Figures and Tables from this paper

Animal Identification in Low Quality Camera-Trap Images Using Very Deep Convolutional Neural Networks and Confidence Thresholds
TLDR
Very deep convolutional neural networks were used to distinguish images, firstly between birds and mammals, secondly between mammals sets, and an alleviation mode using a confidence threshold of automatic classification is proposed, allowing the system to reach 100% of performance traded with human work.
Towards Automatic Detection of Animals in Camera-Trap Images
TLDR
This paper re-train and apply two state-of-the-art deep-learning based object detectors to localize and classify Serengeti animals in camera-trap images and shows that the combination of the results of both detectors can enhance overall mean average precision.
WILD ANIMAL DETECTION AND COUNTING IN CAMERA TRAPS USING OBJECT DETECTION: A REVIEW
TLDR
The objective of this review paper is to highlight the contributions of the use of camera traps in wild areas analysis projects, to relate how machine learning can help in these projects and to identify the approaches proposed to automate the retrieval of information from camera traps images.
Identifying Animals in Camera Trap Images via Neural Architecture Search
TLDR
A search method using regression trees to evaluate candidate networks to lower search costs, and candidate networks are built based on a meta-architecture automatically adjusted regarding to the resource limits of edge devices are proposed.
Animal Recognition and Identification with Deep Convolutional Neural Networks for Automated Wildlife Monitoring
TLDR
A framework to build automated animal recognition in the wild, aiming at an automated wildlife monitoring system is proposed, using a single-labeled dataset from Wildlife Spotter project and the state-of-the-art deep convolutional neural network architectures to train a computational system capable of filtering animal images and identifying species automatically.
Identifying animal species in camera trap images using deep learning and citizen science
TLDR
Ecologists can significantly reduce image classification time and manual effort by combining citizen scientists and CNNs, enabling faster processing of data from large camera trap studies.
Domain-Aware Neural Architecture Search for Classifying Animals in Camera Trap Images
TLDR
A novel search method conducted directly on camera trap images with lowered resolutions and maintained aspect ratios is designed, guided by a loss function whose hyper parameter is theoretically derived for finding lightweight networks.
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
TLDR
The ability to automatically, accurately, and inexpensively collect such data, which could help catalyze the transformation of many fields of ecology, wildlife biology, zoology, conservation biology, and animal behavior into “big data” sciences is investigated.
Machine learning to classify animal species in camera trap images: applications in ecology
TLDR
An r package (Machine Learning for Wildlife Image Classification) is provided that allows the users to use the trained model presented here and train their own model using classified images of wildlife from their studies and makes these methods accessible to ecologists.
Animal Localization in Camera-Trap Images with Complex Backgrounds
TLDR
This paper proposes a system based on Robust Principal Component Analysis (Robust PCA) that spatially localizes the animals in the image and can be integrated into existing models to improve classification and detection accuracy.
...
...

References

SHOWING 1-10 OF 22 REFERENCES
Animal Identification in Low Quality Camera-Trap Images Using Very Deep Convolutional Neural Networks and Confidence Thresholds
TLDR
Very deep convolutional neural networks were used to distinguish images, firstly between birds and mammals, secondly between mammals sets, and an alleviation mode using a confidence threshold of automatic classification is proposed, allowing the system to reach 100% of performance traded with human work.
Deep convolutional neural network based species recognition for wild animal monitoring
TLDR
This is the first attempt to the fully automatic computer vision based species recognition on the real camera-trap images, and it is clear that the proposed deep convolutional neural networkbased species recognition achieves superior performance.
Automated identification of animal species in camera trap images
TLDR
An automated species identification method for wildlife pictures captured by remote camera traps that uses improved sparse coding spatial pyramid matching (ScSPM), which extracts dense SIFT descriptor and cell-structured LBP as the local features and generates global feature via weighted sparse coding and max pooling using multi-scale pyramid kernel.
Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna
TLDR
This work deployed 225 camera traps across Serengeti National Park, Tanzania, to evaluate spatial and temporal inter-species dynamics and classified the images via the citizen-science website www.snapshotsereNGeti.org, yielding a final classification for each image and a measure of agreement among individual answers.
Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection
TLDR
It is found that learning algorithms are surprisingly robust to annotation errors and this level of training data corruption can lead to an acceptably small increase in test error if the training set has sufficient size.
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
TLDR
A series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13 suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.
ImageNet Large Scale Visual Recognition Challenge
TLDR
The creation of this benchmark dataset and the advances in object recognition that have been possible as a result are described, and the state-of-the-art computer vision accuracy with human accuracy is compared.
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
...
...