Recognition of Mammal Genera on Camera-Trap Images Using Multi-layer Robust Principal Component Analysis and Mixture Neural Networks

Giraldo-Zuluaga, Jhony-Heriberto; Salazar, Augusto; Gomez, Alexander; Díaz-Pulido, Angélica

doi:10.1109/ictai.2017.00020

Cited by 16 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even so, the accuracies that were achieved, for example, 82% by Yu et al (2013), were not comparable to human accuracies of 96.6% (Swanson et al, 2016). More recent studies in automatically identifying animal species using CNNs have reported accuracies around 90% with some manual preprocessing (Gomez Villa et al, 2017) or more complex pipelines involving automatic preprocessing (Giraldo-Zuluaga, Salazar, Gomez, & Diaz-Pulido, 2017). The most recent advances by Norouzzadeh et al (2018) have reported accuracies of 93.8% and have matched human accuracy on over 99% of all images.…”

Section: Automatic Animal Identificationmentioning

confidence: 94%

“…(), were not comparable to human accuracies of 96.6% (Swanson et al., ). More recent studies in automatically identifying animal species using CNNs have reported accuracies around 90% with some manual preprocessing (Gomez Villa et al., ) or more complex pipelines involving automatic preprocessing (Giraldo‐Zuluaga, Salazar, Gomez, & Diaz‐Pulido, ). The most recent advances by Norouzzadeh et al.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying animal species in camera trap images using deep learning and citizen science

et al. 2018

View full text Add to dashboard Cite

Ecologists often study wildlife populations by deploying camera traps. Large datasets are generated using this approach which can be difficult for research teams to manually evaluate. Researchers increasingly enlist volunteers from the general public as citizen scientists to help classify images. The growing number of camera trap studies, however, makes it ever more challenging to find enough volunteers to process all projects in a timely manner. Advances in machine learning, especially deep learning, allow for accurate automatic image classification. By training models using existing datasets of images classified by citizen scientists and subsequent application of such models on new studies, human effort may be reduced substantially. The goals of this study were to (a) assess the accuracy of deep learning in classifying camera trap data, (b) investigate how to process datasets with only a few classified images that are generally difficult to model, and (c) apply a trained model on a live online citizen science project. Convolutional neural networks (CNNs) were used to differentiate among images of different animal species, images of humans or vehicles, and empty images (no animals, vehicles, or humans). We used four different camera trap datasets featuring a wide variety of species, different habitats, and a varying number of images. All datasets were labelled by citizen scientists on Zooniverse. Accuracies for identifying empty images across projects ranged between 91.2% and 98.0%, whereas accuracies for identifying specific species were between 88.7% and 92.7%. Transferring information from CNNs trained on large datasets (“transfer‐learning”) was increasingly beneficial as the size of the training dataset decreased and raised accuracy by up to 10.3%. Removing low‐confidence predictions increased model accuracies to the level of citizen scientists. By combining a trained model with classifications from citizen scientists, human effort was reduced by 43% while maintaining overall accuracy for a live experiment running on Zooniverse. Ecology researchers 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.

show abstract

Section: Automatic Animal Identificationmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Identifying animal species in camera trap images using deep learning and citizen science

et al. 2018

View full text Add to dashboard Cite

show abstract

“…These standards are a powerful tool to environmentalists as camera traps can document all wildlife aspects. Camera trapping is being carried out quickly in the field of wildlife monitoring with digital technological improvements, which produce more contemporary camera traps with system part automation, but reduce costs for procurement [26,38]. Although the human visual system can quickly and easily process images, manually manipulating such a large amount of images is still very costly.…”

Section: Animal Detection Methods In Field Of Image Processingmentioning

confidence: 99%

Scrutiny of Methods for Image Detection and Recognition of Different Species of Animals

2019

IJRTE

View full text Add to dashboard Cite

Animal detection-based study is useful in many real-life applications. Techniques involved in animal detection are useful in observing the locomotive behavior of the engaged animal and in result it prevent harmful interruption of animals in residential areas. There are some branches of research in animal detection. Some of these branches will therefore be discussed in this journal. Humans have developed many algorithms and techniques to gain a better understanding of animal behaviour. Therefore, for early preventive measures, these technologies can also serve as a warning system for humans from encroachment of dangerous wild animals. Such tasks can be reduced to three main branches, namely animal detection, tracking and recognition. Through these papers, new approaches for study and a variety of technologies/algorithms implemented in the past are identified and appropriate ways for solving the research gaps are suggested to fill the gap.

show abstract

“…Animal segmentation using Multi-Layer Robust Principal Component Analysis involving color and texture features was proposed in [16]. This approach was further combined with deep learning methods in [15]. Both works are evaluated on camera trap data from a Colombian forest.…”

Section: Automated Wildlife Surveillancementioning

confidence: 99%

Active and Incremental Learning with Weak Supervision

2020

View full text Add to dashboard Cite

Note: This paper is an extended version of our previous work [4], from which certain parts of sections 2 to 5 (except novel YOLO-specific methods) were taken verbatim. Section 8 contains some verbatim parts from our previous work [33].Abstract Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only asking for respective labels, active learning can increase the efficiency of the labeling process in terms of time and cost.In this work, we describe combinations of an incremental learning scheme and methods of active learning. These allow for continuous exploration of newly observed unlabeled data. We describe selection criteria based on model uncertainty as well as expected model output change (E-MOC). An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset. We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application where images from camera traps are analyzed. Labeling only 32 images by accepting or rejecting proposals gen-

show abstract

Recognition of Mammal Genera on Camera-Trap Images Using Multi-layer Robust Principal Component Analysis and Mixture Neural Networks

Cited by 16 publications

References 20 publications

Identifying animal species in camera trap images using deep learning and citizen science

Identifying animal species in camera trap images using deep learning and citizen science

Scrutiny of Methods for Image Detection and Recognition of Different Species of Animals

Active and Incremental Learning with Weak Supervision

Contact Info

Product

Resources

About