RETRACTED CHAPTER: UAVs Applied to the Counting and Monitoring of Animals

Chamoso, Pablo; Raveane, William; Parra, Víctor; González, Angélica

doi:10.1007/978-3-319-07596-9_8

Cited by 73 publications

(47 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Agro-forested areas seemingly require adapted methods, e.g. based on new technologies such as drone for animal detection (Chamoso et al 2014) in crop fields, which could help hunters in their management activities.…”

Section: Management Implicationsmentioning

confidence: 99%

Seasonal variations of wild boar Sus scrofa distribution in agricultural landscapes: a species distribution modelling approach

Мorelle

Lejeune

2014

Eur J Wildl Res

View full text Add to dashboard Cite

Seasonal changes in the distribution of animals can have an important impact on the ecosystem. In agricultural landscapes, the seasonal movement of the wild boar Sus scrofa towards field crops often results in damages and makes control of the population difficult. The plasticity of the species to cope with different habitats is largely proven, but the environmental and human drivers of this seasonal habitat shift at the population scale remain largely unknown. Using MaxEnt and two seasonally distinct presence datasets, we contrasted the distribution of wild boar in southern Belgium during the growing and hunting seasons to (i) analyse seasonal drivers of the distribution and (ii) forecast the potential spread of the species north to its current distribution. We demonstrated that during the growing season, wild boar range almost double, owing to the cover and food provided by agricultural areas, thereby enhancing the movement and spread of the species. We found that the seasonal distribution of wild boar in agricultural lands is mostly influenced by the search for cover and food provided alternatively by forest and field crops. Interestingly, it seems that this search for cover operates under the constraint of a threshold distance. Our results indeed reveal an increased probability of presence not only in the vicinity of forests but also above a threshold distance of 865 m from the forest edge, suggesting that wild boar can overcome the dependence to forest cover. The forecast distribution of wild boar highlighted a potential increase of the current range into suitable habitat between 63 and 168 km 2 . To counteract the potential spread of the species into agricultural habitats and the consecutive damages, we insist on the need for the development of integrated management strategies, combining land use spatial configuration and wild boar spatial behaviour.

show abstract

Section: Management Implicationsmentioning

confidence: 99%

Seasonal variations of wild boar Sus scrofa distribution in agricultural landscapes: a species distribution modelling approach

Мorelle

Lejeune

2014

Eur J Wildl Res

View full text Add to dashboard Cite

show abstract

“…Estimating population sizes of animals is key in nature conservation (Davis & Winstead, ; Norton‐Griffiths, ; Van Lavieren, ) and large‐scale animal husbandry (Andrew, Greatwood, & Burghardt, ; Chamoso, Raveane, Parra, & González, ). Accurate animal population estimates are important for farmers to determine the value of their companies and for game managers to optimize hunting strategies (Hearne, Korrûbel, & Koch, ; Mwakiwa et al, ; Van Lavieren, ), while precise estimates are important to follow population trends of rare and/or valuable wildlife species (Van Lavieren, ).…”

Section: Introductionmentioning

confidence: 99%

Improving the precision and accuracy of animal population estimates with aerial image object detection

et al. 2019

View full text Add to dashboard Cite

Animal population sizes are often estimated using aerial sample counts by human observers, both for wildlife and livestock. The associated methods of counting remained more or less the same since the 1970s, but suffer from low precision and low accuracy of population estimates. Aerial counts using cost‐efficient Unmanned Aerial Vehicles or microlight aircrafts with cameras and an automated animal detection algorithm can potentially improve this precision and accuracy. Therefore, we evaluated the performance of the multi‐class convolutional neural network RetinaNet in detecting elephants, giraffes and zebras in aerial images from two Kenyan animal counts. The algorithm detected 95% of the number of elephants, 91% of giraffes and 90% of zebras that were found by four layers of human annotation, of which it correctly detected an extra 2.8% of elephants, 3.8% giraffes and 4.0% zebras that were missed by all humans, while detecting only 1.6 to 5.0 false positives per true positive. Furthermore, the animal detections by the algorithm were less sensitive to the sighting distance than humans were. With such a high recall and precision, we posit it is feasible to replace manual aerial animal count methods (from images and/or directly) by only the manual identification of image bounding boxes selected by the algorithm and then use a correction factor equal to the inverse of the undercounting bias in the calculation of the population estimates. This correction factor causes the standard error of the population estimate to increase slightly compared to a manual method, but this increase can be compensated for when the sampling effort would increase by 23%. However, an increase in sampling effort of 160% to 1,050% can be attained with the same expenses for equipment and personnel using our proposed semi‐automatic method compared to a manual method. Therefore, we conclude that our proposed aerial count method will improve the accuracy of population estimates and will decrease the standard error of population estimates by 31% to 67%. Most importantly, this animal detection algorithm has the potential to outperform humans in detecting animals from the air when supplied with images taken at a fixed rate.

show abstract

“…The livestock surveillance is a more reliable solution through UAVs to scan the large area very easily for counting the animals throughout making the videos. The animal can be tracked or analyzed through the recorded video or images (Chamoso, Raveane, Parra, & González, 2014). The UAVs have been considered for livestock monitoring, several peoples do not know that UAVs are used for monitoring the cattle in real, they know that this is science fiction.…”

Section: Uav In Livestock Surveillancementioning

confidence: 99%