Detection of dugongs from unmanned aerial vehicles

Maire, Frédéric; Mejias, Luís; Hodgson, Amanda; Duclos, Gwenael

doi:10.1109/iros.2013.6696745

Cited by 16 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…() developed techniques to detect whales at or near the water surface based on spectral characteristics, and Maire et al. (, ) and Mejias et al. () developed OBIA approaches similar to those described above for birds to detect dugongs ( Dugong dugon ) in high‐resolution UAS images.…”

Section: Overview Of Image‐analysis Techniquesmentioning

confidence: 99%

Computer-automated bird detection and counts in high-resolution aerial images: a review

2016

View full text Add to dashboard Cite

Bird surveys conducted using aerial images can be more accurate than those using airborne observers, but can also be more time‐consuming if images must be analyzed manually. Recent advances in digital cameras and image‐analysis software offer unprecedented potential for computer‐automated bird detection and counts in high‐resolution aerial images. We review the literature on this subject and provide an overview of the main image‐analysis techniques. Birds that contrast sharply with image backgrounds (e.g., bright birds on dark ground) are generally the most amenable to automated detection, in some cases requiring only basic image‐analysis software. However, the sophisticated analysis capabilities of modern object‐based image analysis software provide ways to detect birds in more challenging situations based on a variety of attributes including color, size, shape, texture, and spatial context. Some techniques developed to detect mammals may also be applicable to birds, although the prevalent use of aerial thermal‐infrared images for detecting large mammals is of limited applicability to birds because of the low pixel resolution of thermal cameras and the smaller size of birds. However, the increasingly high resolution of true‐color cameras and availability of small unmanned aircraft systems (drones) that can fly at very low altitude now make it feasible to detect even small shorebirds in aerial images. Continued advances in camera and drone technology, in combination with increasingly sophisticated image analysis software, now make it possible for investigators involved in monitoring bird populations to save time and resources by increasing their use of automated bird detection and counts in aerial images. We recommend close collaboration between wildlife‐monitoring practitioners and experts in the fields of remote sensing and computer science to help generate relevant, accessible, and readily applicable computer‐automated aerial photographic census techniques.

show abstract

Section: Overview Of Image‐analysis Techniquesmentioning

confidence: 99%

Computer-automated bird detection and counts in high-resolution aerial images: a review

2016

View full text Add to dashboard Cite

show abstract

“…Detection of Florida manatees by hand-launched fixed-wing UAS was reported by Jones et al (2006) and Martin et al (2012). Hodgson et al (2013) used a larger catapult-launched system to survey dugongs (Dugong dugon) in Shark Bay, Australia, followed by the development of an algorithm to automatically detect the animals in the imagery (Maire et al 2013). Pinnipeds are similarly amenable to small-scale UAS surveys because of their tendency to congregate at rookeries and haul-out sites.…”

Section: Mammalsmentioning

confidence: 99%

“…Several of the above-cited studies attempted, with varying degrees of success, various digital image analysis techniques for automated detection and (or) counting of animals (Abd-Elrahman et al 2005;Selby et al 2011;Chabot and Bird 2012;Grenzdorffer 2013;Maire et al 2013;Christiansen et al 2014;van Gemert et al 2015). Numerous additional examples of similar automated analysis techniques applied to imagery acquired by conventional aircraft are available in the broader wildlife literature (e.g., Laliberte and Ripple 2003;Descamps et al 2011;Groom et al 2013).…”

Section: Herptilesmentioning

confidence: 99%

Wildlife research and management methods in the 21st century: Where do unmanned aircraft fit in?

Chabot

Bird

2015

J. Unmanned Veh. Sys.

218

183

View full text Add to dashboard Cite

Since the turn of the century, emerging unmanned aircraft systems (UAS) have found increasingly diverse applications in wildlife science as convenient, very highresolution remote sensing devices. Achieved or conceptualized applications include optical surveying and observation of animals, autonomous wildlife telemetry tracking, and habitat research and monitoring. As the technology continues to progress and interest from the wildlife science community grows, there may yet be much untapped potential for UAS to contribute to the discipline. We present a review of the published primary literature on the application of UAS in wildlife science and related fields. This is followed by a systematic review of the broader wildlife science literature published since the turn of the century to assess where UAS are likely to make important contributions going forward based on the trends that have emerged thus far. UAS, in particular small lightweight models, are generally well suited for collecting data at an intermediate spatial scale between what is easily coverable on the ground and what is economically coverable with conventional aircraft. They are particularly useful for monitoring wildlife and habitats in places that are difficult to access or navigate from the ground, as well as approaching sensitive or aggressive species.Key words: aerial survey, conservation, remotely piloted aircraft system, unmanned aerial vehicle, drone, wildlife monitoring.Résumé : Depuis le début du siècle, les nouveaux systèmes d'aéronefs sans pilote (UAS), en tant qu'appareils de télédétection de haute résolution pratiques, ont donné lieu à de plus en plus d'applications diverses en science de la faune. Les applications réalisées ou conceptualisées comprennent l'inventaire et l'observation optiques des animaux, la localisation autonome de la faune par télémétrie et la recherche et la surveillance des habitats. À mesure que la technologie continue de progresser et que l'intérêt de la part du milieu scientifique du domaine de la faune croît, la contribution des UAS à la discipline pourra augmenter, car il peut y avoir encore beaucoup de potentiel à exploiter. Nous présentons un examen de la littérature primaire publiée portant sur l'application des UAS dans les domaines de la science de la faune et connexes. Un examen systématique de l'ensemble de la littérature de la science de la faune publiée depuis le début du siècle s'ensuit dans le but d'évaluer, d'après les tendances qui ont émergé jusqu'à maintenant, où les UAS vont possiblement faire des contributions à l'avenir. Les UAS, en particulier les petits modèles légers, sont bien adaptés à la collecte de données à une échelle spatiale intermédiaire entre ce qui est facilement saisi sur le terrain et ce qui est saisi à l'aide d'un aéronef traditionnel. Ils sont particulièrement utiles pour la surveillance de la faune et des habitats dans les endroits difficiles à accéder ou à naviguer à partir du sol, ainsi que pour s'approcher des espèces sensibles ou agressives.

show abstract

“…Now with the help of aerial photography, it has become easier to capture thousands of images over the oceans, but the real challenge is to identify sea cows in those photos. Dr. Amanda Hodgson of Murdoch University teamed up with Dr. Frederic Maire, a computer scientist at Queensland University of Technology and using tensorflow built a detector that could learn to find sea cows in these photos automatically [3].…”

Section: Studying the Behaviour Of Rare Or Elusive Animal Speciesmentioning

confidence: 99%

Harnessing the Power of Deep Learning to Save Animals

Mridula¹,

Bonde²

2017

IJCA

View full text Add to dashboard Cite

During the last decade, AI has become the most important field for the researchers to provide a solutions for real world's challenges, resulting in the new emerged field of deep learning which make the system more efficient and optimized .This paper discusses the expansion of deep learning towards the welfare of animal life considering ways to save them and monitoring their count and health conditions. Techniques like image classification and object detection can provide plethora of information that can assist in conducting study on various aspects by identifying and classifying these animal species from thousands of images captured by drones or cameras which could be very strenuous and tedious to be done by humans.

show abstract

Detection of dugongs from unmanned aerial vehicles

Cited by 16 publications

References 21 publications

Computer-automated bird detection and counts in high-resolution aerial images: a review

Computer-automated bird detection and counts in high-resolution aerial images: a review

Wildlife research and management methods in the 21st century: Where do unmanned aircraft fit in?

Harnessing the Power of Deep Learning to Save Animals

Contact Info

Product

Resources

About