Filters








342 Hits in 6.7 sec

Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning [article]

Mohammed Sadegh Norouzzadeh, Anh Nguyen, Margaret Kosmala, Ali Swanson, Meredith Palmer, Craig Packer, Jeff Clune
2017 arXiv   pre-print
Those efficiency gains immediately highlight the importance of using deep neural networks to automate data extraction from camera-trap images.  ...  We train deep convolutional neural networks to identify, count, and describe the behaviors of 48 species in the 3.2-million-image Snapshot Serengeti dataset.  ...  Gomez A, Diez G, Salazar A, Diaz A (2016) Animal identification in low quality camera-trap images using very deep convolutional neural networks and confidence thresholds in International Symposium on Visual  ... 
arXiv:1703.05830v5 fatcat:5ip5ine4czhshieovcue2ellli

Species‐level image classification with convolutional neural network enables insect identification from habitus images

Oskar L. P. Hansen, Jens‐Christian Svenning, Kent Olsen, Steen Dupont, Beulah H. Garner, Alexandros Iosifidis, Benjamin W. Price, Toke T. Høye
2019 Ecology and Evolution  
Here, we test whether a convolutional neural network (CNN) can classify habitus images of ground beetles to species level, and estimate how correct classification relates to body size, number of species  ...  Camera traps can capture habitus images of ground-dwelling insects. However, currently sampling involves manually detecting and identifying specimens.  ...  | Evaluating predictions and setting thresholds to separate low-and high-confidence predictions The output layer of the convolutional neural network consisted of a The neural network included only species-level  ... 
doi:10.1002/ece3.5921 pmid:32015839 pmcid:PMC6988528 fatcat:e3otvlsdx5gv3k2mruc7q223cm

A deep active learning system for species identification and counting in camera trap images [article]

Mohammad Sadegh Norouzzadeh, Dan Morris, Sara Beery, Neel Joshi, Nebojsa Jojic, Jeff Clune
2019 arXiv   pre-print
However, extracting useful information from camera trap images is a cumbersome process: a typical camera trap survey may produce millions of images that require slow, expensive manual review.  ...  camera trap images.  ...  Deep convolutional neural networks are a class of deep neural networks designed specifically to process images [8, 15] .  ... 
arXiv:1910.09716v1 fatcat:xqrxsaf5obbqxpksictfildjwa

Automated location invariant animal detection in camera trap images using publicly available data sources

Andrew Shepley, Greg Falzon, Paul Meek, Paul Kwan
2021 Ecology and Evolution  
location invariant camera trap object detectors by (a) evaluating publicly available image datasets characterized by high intradataset variability in training deep learning models for camera trap object  ...  This prevents optimal use of ecological data resulting in significant expenditure of time and resources to annotate and retrain deep learning models.We present a method ecologists can use to develop optimized  ...  K E Y W O R D S animal identification, artificial intelligence, camera trap images, camera trapping, deep convolutional neural networks, deep learning, infusion, location invariance, wildlife ecology,  ... 
doi:10.1002/ece3.7344 pmid:33976825 pmcid:PMC8093655 fatcat:3lj5xjnmnfajvdtgri3lh227qa

Florida Wildlife Camera Trap Dataset [article]

Crystal Gagne, Jyoti Kini, Daniel Smith, Mubarak Shah
2021 arXiv   pre-print
We introduce a challenging wildlife camera trap classification dataset collected from two different locations in Southwestern Florida, consisting of 104,495 images featuring visually similar species, varying  ...  Minimal human interference required to operate camera traps allows capturing unbiased species activities.  ...  Animal identification in low quality camera-trap images using very deep convolutional neural networks and confidence thresholds. In International symposium on visual computing, pages 747-756.  ... 
arXiv:2106.12628v1 fatcat:6obg5al52nbd7jhdlxj22az634

Three critical factors affecting automated image species recognition performance for camera traps

Stefan Schneider, Saul Greenberg, Graham W. Taylor, Stefan C. Kremer
2020 Ecology and Evolution  
The success of deep learning systems using camera trap images has been previously explored in preliminary stages. These studies, however, are lacking in their practicality.  ...  Ecological camera traps are increasingly used by wildlife biologists to unobtrusively monitor an ecosystems animal population.  ...  Following this work, they also used deep learning to improve low-resolution animal species recognition by training deep CNNs on poor-quality images.  ... 
doi:10.1002/ece3.6147 pmid:32274005 pmcid:PMC7141055 fatcat:m3mabgop2zf2dp7dsogprm3rui

Deep learning‐based methods for individual recognition in small birds

André C. Ferreira, Liliana R. Silva, Francesco Renna, Hanja B. Brandl, Julien P. Renoult, Damien R. Farine, Rita Covas, Claire Doutrelant, Edward Codling
2020 Methods in Ecology and Evolution  
| INTRODUC TI ON In recent years, deep learning techniques, such as convolutional neural networks (CNNs), have caught the attention of ecologists.  ...  K E Y W O R D S artificial intelligence, automated, convolutional neural networks, data collection, deep learning, individual identification images with the identity (or an attribute) of each individual  ... 
doi:10.1111/2041-210x.13436 fatcat:arxtggz7yfd2rctgta22y6bv4m

Filtering Empty Camera Trap Images in Embedded Systems [article]

Fagner Cunha, Eulanda M. dos Santos, Raimundo Barreto, Juan G. Colonna
2021 arXiv   pre-print
Embedding deep learning models to identify animals and filter these images directly in those devices brings advantages such as savings in the storage and transmission of data, usually resource-constrained  ...  Monitoring wildlife through camera traps produces a massive amount of images, whose a significant portion does not contain animals, being later discarded.  ...  The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.  ... 
arXiv:2104.08859v1 fatcat:yrhbejwwqrh4texurmq52zjxtu

Innovations in Camera Trapping Technology and Approaches: The Integration of Citizen Science and Artificial Intelligence

Green, Rees, Stephens, Hill, Giordano
2020 Animals  
As camera trap technology has evolved, cameras have become more user-friendly and the enormous quantities of data they now collect has led researchers to seek assistance in classifying footage.  ...  Camera trapping has become an increasingly reliable and mainstream tool for surveying a diversity of wildlife species.  ...  Acknowledgments: We would like to thank Samantha Mason and the anonymous reviewers for their constructive and helpful feedback on earlier drafts of this manuscript.  ... 
doi:10.3390/ani10010132 pmid:31947586 pmcid:PMC7023201 fatcat:h3uhrx5l4nbzrb4rippeqtrkuu

Deep learning-based methods for individual recognition in small birds [article]

André C. Ferreira, Liliana R. Silva, Francesco Renna, Hanja B. Brandl, Julien P. Renoult, Damien R. Farine, Rita Covas, Claire Doutrelant
2019 biorxiv/medrxiv   pre-print
neural networks (CNNs).Here, we describe procedures that improve data collection and allow individual identification in captive and wild birds and we apply it to three small bird species, the sociable  ...  Third, we illustrate the general applicability of CNN for individual identification in animal studies by showing that the trained CNN can predict the identity of birds from images collected in contexts  ...  | INTRODUC TI ON In recent years, deep learning techniques, such as convolutional neural networks (CNNs), have caught the attention of ecologists.  ... 
doi:10.1101/862557 fatcat:bopisi6hzfhnde7z2pfuctq6fi

The Role of Citizen Science and Deep Learning in Camera Trapping

Matyáš Adam, Pavel Tomášek, Jiří Lehejček, Jakub Trojan, Tomáš Jůnek
2021 Sustainability  
and citizens' evaluations, the way of training a neural network and adding a taxon complexity index.  ...  Our approach aims to show a new perspective and to update the recent progress in engaging the enthusiasm of citizen scientists and in including machine learning processes into image classification in camera  ...  Acknowledgments: We are grateful to Dušan Romportl, whose long-term experience in the field has helped to form the idea of creating the camera trap database and whose input has improved the features of  ... 
doi:10.3390/su131810287 fatcat:xa7nvzd47vbhjc4wgtysv4azui

ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images

Falzon, Lawson, Cheung, Vernes, Ballard, Fleming, Glen, Milne, Mather-Zardain, Meek
2019 Animals  
We present ClassifyMe a software tool for the automated identification of animal species from camera trap images. ClassifyMe is intended to be used by ecologists both in the field and in the office.  ...  ClassifyMe will identify animals and other objects (e.g., vehicles) in images, provide a report file with the most likely species detections, and automatically sort the images into sub-folders corresponding  ...  Acknowledgments: We thank the following funding bodies for supporting our endeavours to provide a range of practitioner-based tools using current technology: Australian Wool Innovation, Meat and Livestock  ... 
doi:10.3390/ani10010058 pmid:31892236 pmcid:PMC7022311 fatcat:dy65llirrvdmzagb3wboogflde

Automated cattle counting using Mask R-CNN in quadcopter vision system

Beibei Xu, Wensheng Wang, Greg Falzon, Paul Kwan, Leifeng Guo, Guipeng Chen, Amy Tait, Derek Schneider
2020 Computers and Electronics in Agriculture  
The optimal IoU threshold (0.5) and the full-appearance detection for the algorithm in this study are verified through performance evaluation.  ...  Our research shows promising steps towards the incorporation of artificial intelligence using quadcopters for enhanced management of animals.  ...  In contrast, more recent objection approaches combine artificial neural network and deep learning technology via the convolutional neural network, which has combined local region perception, feature extraction  ... 
doi:10.1016/j.compag.2020.105300 fatcat:lp5rh2k2aza73eiu3ddzikgcki

ClassifyMe: a field-scouting software for the identification of wildlife in camera trap images [article]

Greg Falzon, Christopher Lawson, Ka-Wai Cheung, Karl Vernes, Guy Ballard, Peter JS Fleming, Al Glen, Heath Milne, Atalya Mather-Zardain, Paul D Meek
2019 bioRxiv   pre-print
We present ClassifyMe a software tool for the automated identification of animal species from camera trap images. ClassifyMe is intended to be used by ecologists both in the field and in the office.  ...  ClassifyMe will identify animals and other objects (e.g. vehicles) in images, provide a report file with the most likely species detections and automatically sort the images into sub-folders corresponding  ...  The dataset is described in and features camera trap images of 40 mammal species on the African savanna.  ... 
doi:10.1101/646737 fatcat:cq56rgkmqnccpompxsvhmmpubu

High Throughput Data Acquisition and Deep Learning for Insect Ecoinformatics

Alexander Gerovichev, Achiad Sadeh, Vlad Winter, Avi Bar-Massada, Tamar Keasar, Chen Keasar
2021 Frontiers in Ecology and Evolution  
The proposed approach combines "high tech" deep learning with "low tech" sticky traps that sample flying insects in diverse locations.  ...  We developed software, based on deep learning, to identify the three species in images of sticky traps from Eucalyptus forests.  ...  The current leading approach to such tasks is supervised learning using deep neural networks (DNNs), and particularly convolutional neural networks (CNNs), which are able to extract abstract high level  ... 
doi:10.3389/fevo.2021.600931 fatcat:gojrd67lizb33p6tyyyt5fqqim
« Previous Showing results 1 — 15 out of 342 results