Corpus ID: 189762336

Amur Tiger Re-identification in the Wild

@article{Li2019AmurTR,
  title={Amur Tiger Re-identification in the Wild},
  author={Shuyuan Li and Jianguo Li and Weiyao Lin and Hanlin Tang},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.05586}
}
Monitoring the population and movements of endangered species is an important task to wildlife conversation. Traditional tagging methods do not scale to large populations, while applying computer vision methods to camera sensor data requires re-identification (re-ID) algorithms to obtain accurate counts and moving trajectory of wildlife. However, existing re-ID methods are largely targeted at persons and cars, which have limited pose variations and constrained capture environments. This paper… Expand
Part-Pose Guided Amur Tiger Re-Identification
TLDR
A novel part-pose guided framework for the tiger re-ID task, which consists of two part streams and one full stream based on the pose characteristics of tiger, which outperforms the state-of-the-art and finished top in both the PlainID and WildID competitions at CVWC2019. Expand
Pose-Guided Complementary Features Learning for Amur Tiger Re-Identification
TLDR
This paper simplifies tiger poses as right-headed or left-headed and utilizes this information as an auxiliary pose classification task to supervise the feature learning to improve the Amur tiger re-identification accuracy. Expand
Detection Features as Attention (Defat): A Keypoint-Free Approach to Amur Tiger Re-Identification
TLDR
This paper devise a detection-features-as-attention (DeFAt) module, which generates an additive mask for the input image based on the detection feature maps, and proves that the proposed DeFAt module can effectively improve the Amur tiger re-identification accuracy when key-point annotations are not available. Expand
Deep Learning Methods for Multi-Species Animal Re-identification and Tracking - a Survey
TLDR
The applicability of existing animal re-identification techniques for fully automated individual animal tracking in a cross-camera setup is explored and common trends in re-Identification methods are presented, lists a few challenges in the domain and recommends possible solutions. Expand
A Strong Baseline for Tiger Re-ID and its Bag of Tricks
TLDR
A novel dynamic partial matching method that performs an alignment/matching by flipping local features and calculating the shortest path between them and the superiority of this method for tiger Re-ID is validated. Expand
Learning Landmark Guided Embeddings for Animal Re-identification
TLDR
This work proposes to improve embedding learning by exploiting body landmarks information explicitly by outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively. 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
Semi-supervised Keypoint Localization
TLDR
This work proposes to learn simultaneously keypoint heatmaps and pose invariant keypoint representations in a semi-supervised manner using a small set of labeled images along with a larger set of unlabeled images to reduce the need for labeled data. Expand
YOLO-mini-tiger: Amur Tiger Detection
TLDR
An efficient deep tiger detector, which consists of the convnet channel adaptation method and an improved tiger detection method based on You Only Look Once version 3, which outperforms previous Amur tiger detection methods presented at CVWC2019. Expand
Animal Detection in Man-made Environments
TLDR
Empirical evidence is presented to demonstrate the inability of detectors to generalize from training images of animals in their natural habitats to deployment scenarios of man-made environments and a solution is proposed using semi-automated synthetic data generation for domain specific training. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 49 REFERENCES
Person Re-identification in the Wild
TLDR
A new dataset, PRW, is introduced to evaluate Person Re-identification in the Wild, and it is shown that pedestrian detection aids re-ID through two simple yet effective improvements: a cascaded fine-tuning strategy that trains a detection model first and then the classification model, and a Confidence Weighted Similarity (CWS) metric that incorporates detection scores into similarity measurement. Expand
Past, Present, and Future Approaches Using Computer Vision for Animal Re-Identification from Camera Trap Data
TLDR
It is expected that this methodology will allow ecologists with camera/video trap data to re-identify individuals that exit and re-enter the camera frame and could stand to revolutionize the analysis of camera trap data and, ultimately, the approach to animal ecology. Expand
Towards Automatic Identification of Elephants in the Wild
TLDR
A system for identifying elephants in the face of a large number of individuals with only few training images per individual is presented, combining object part localization, off-the-shelf CNN features, and support vector machine classification to provide field researches with proposals of possible individuals given new images of an elephant. Expand
Scalable Person Re-identification: A Benchmark
TLDR
A minor contribution, inspired by recent advances in large-scale image search, an unsupervised Bag-of-Words descriptor is proposed that yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large- scale 500k dataset. Expand
Assessing tiger population dynamics using photographic capture-recapture sampling.
TLDR
The ability to model the entire photographic capture history data set and incorporate reduced-parameter models led to estimates of mean annual population change that were sufficiently precise to be useful, consistent with the hypothesis that protected wild tiger populations can remain healthy despite heavy mortalities. Expand
Improving Person Re-identification by Attribute and Identity Learning
TLDR
An attribute-person recognition (APR) network is proposed, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes, and demonstrates that by learning a more discriminative representation, APR achieves competitive re-IDs performance compared with the state-of-the-art methods. Expand
DeepReID: Deep Filter Pairing Neural Network for Person Re-identification
TLDR
A novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter is proposed and significantly outperforms state-of-the-art methods on this dataset. Expand
Pose-Invariant Embedding for Deep Person Re-Identification
TLDR
This paper introduces pose-invariant embedding (PIE) as a pedestrian descriptor and shows that PoseBox alone yields decent re-ID accuracy and that when integrated in the PBF network, the learned PIE descriptor produces competitive performance compared with state-of-the-art approaches. Expand
GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
TLDR
A Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework that leverages the local and global cues in human body to generate a discriminative and robust representation are proposed. Expand
2D Human Pose Estimation: New Benchmark and State of the Art Analysis
TLDR
A novel benchmark "MPII Human Pose" is introduced that makes a significant advance in terms of diversity and difficulty, a contribution that is required for future developments in human body models. Expand
...
1
2
3
4
5
...