Corpus ID: 118644248

The iWildCam 2018 Challenge Dataset

@article{Beery2019TheI2,
  title={The iWildCam 2018 Challenge Dataset},
  author={Sara Beery and Grant Van Horn and Oisin Mac Aodha and Pietro Perona},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.05986}
}
Camera traps are a valuable tool for studying biodiversity, but research using this data is limited by the speed of human annotation. With the vast amounts of data now available it is imperative that we develop automatic solutions for annotating camera trap data in order to allow this research to scale. A promising approach is based on deep networks trained on human-annotated images. We provide a challenge dataset to explore whether such solutions generalize to novel locations, since systems… Expand
The iWildCam 2020 Competition Dataset
TLDR
This work has prepared a challenge where the training data and test data are from different cameras spread across the globe, and the challenge is to correctly classify species in the test camera traps. Expand
The iWildCam 2019 Challenge Dataset
TLDR
A dataset and challenge where the training data and test data are from different regions, namely The American Southwest and the American Northwest, and allows competitors to utilize transfer learning from two alternate domains: human-curated images from iNaturalist and synthetic images from Microsoft's TrapCam-AirSim simulation environment. Expand
Three critical factors affecting automated image species recognition performance for camera traps
TLDR
The capabilities of deep learning systems trained on camera trap images using modestly sized training data are tested, performance when considering unseen background locations is compared, and the gradient of lower bound performance is quantified to provide a guideline of data requirements in correspondence to performance expectations. Expand
Unifying data for fine-grained visual species classification
TLDR
An initial deep convolutional neural network model is presented, trained on 2.9M images across 465 fine-grained species, with a goal to reduce the load on human experts to classify species in images manually. Expand
The iWildCam 2021 Competition Dataset
TLDR
A challenge where the training data and test data are from different cameras spread across the globe, but the set of species seen in each camera overlap, but are not identical, to classify species and count individual animals across sequences in the test cameras. Expand
Automated detection of European wild mammal species in camera trap images with an existing and pre-trained computer vision model
TLDR
The usability of a pre-trained deep learning model available on the TensorFlow hub–FasterRCNN+InceptionResNet V2 network applied to images of ten different European wild mammal species, showing the potential of an existing and pre- trained image classification model for wildlife animal detection, classification, and analysis. Expand
Image-to-Image Translation of Synthetic Samples for Rare Classes
TLDR
The use of image-to-image translation methods to close the domain gap between synthetic and real imagery for animal species classification in data collected from camera traps: motion-activated static cameras used to monitor wildlife. Expand
Efficient Method for Categorize Animals in the Wild
TLDR
This work proposes an efficient method for categorizing animals in the wild, and transfers the state-of-the-art ImagaNet pretrained models to the problem, to improve the generalization and robustness of the model. Expand
ELPephants: A Fine-Grained Dataset for Elephant Re-Identification
TLDR
The ELPephants dataset is introduced, a re-identification dataset, which contains 276 elephant individuals in 2078 images following a long-tailed distribution, and a baseline approach is presented, which is a system using a YOLO object detector, feature extraction of ImageNet features and discrimination using a support vector machine. Expand
Image identification of Protea species with attributes and subgenus scaling
TLDR
This work considers the problem of identifying the Protea species in a given image with additional (but optional) attributes linked to the observation, such as location and date, and proposes a probabilistic model on the additional attributes associated with the observation. Expand
...
1
2
...

References

SHOWING 1-10 OF 16 REFERENCES
Automatically identifying wild animals in camera trap images with deep learning
TLDR
This paper uses the existing human-labeled images from the Snapshot Serengeti dataset to train deep convolutional neural networks for identifying 48 species in 3.2 million images taken from Tanzania's Serengenti National Park, and trains neural networks that automatically identify animals with over 92% accuracy. Expand
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. Expand
Towards automatic wild animal monitoring: Identification of animal species in camera-trap images using very deep convolutional neural networks
TLDR
The proposed method for animal species identification in the wild using very deep convolutional neural networks outperforms previous approximations and proves that recognition in camera-trap images can be automated. Expand
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. Expand
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. Expand
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. Expand
Animal Detection From Highly Cluttered Natural Scenes Using Spatiotemporal Object Region Proposals and Patch Verification
TLDR
The proposed spatiotemporal object proposal and patch verification framework outperforms the state-of-the-art methods, including the recent Faster-RCNN method, on animal object detection accuracy by up to 4.5%. Expand
Coupled ensemble graph cuts and object verification for animal segmentation from highly cluttered videos
  • Zhi Zhang, T. Han, Z. He
  • Computer Science
  • 2015 IEEE International Conference on Image Processing (ICIP)
  • 2015
TLDR
This paper considers animal object segmentation from wildlife monitoring videos captured by motion-triggered cameras, called camera-traps as an ensemble of frame-level background-foreground object classifiers which fuse information across frames and refine their segmentation results in a collaborative and iterative manner. Expand
Fast human-animal detection from highly cluttered camera-trap images using joint background modeling and deep learning classification
TLDR
This paper develops an effective background modeling and subtraction scheme to generate region proposals for the foreground objects and performs complexity-accuracy analysis of deep convolutional neural networks to develop a fast deep learning classification scheme. Expand
Finding areas of motion in camera trap images
TLDR
This research introduces techniques that find motion in camera trap images that are robust to changes in illumination due to time of day or the presence of camera flash. Expand
...
1
2
...