المؤلفون: Delplanque, Alexandre, Linchant, Julie, Vincke, Xavier, Lamprey, Richard, Théau, Jérôme, Vermeulen, Cédric, Foucher, Samuel, Ouattara, Amara, Kouadio, Roger, Lejeune, Philippe

المصدر: Ecological Informatics, 82, 102679 (2024-06)

مصطلحات موضوعية: aerial survey, deep learning, wildlife, african mammals, population estimation, biodiversity monitoring, conservation technology, african savanna, elephant, buffalo, kob, roan antelope, waterbuck, warthog, hartebeest, Life sciences, Zoology, Environmental sciences & ecology, Engineering, computing & technology, Sciences du vivant, Zoologie, Sciences de l’environnement & écologie, Ingénierie, informatique & technologie

الوصف: Large African mammal populations are traditionally estimated using the systematic reconnaissance flights (SRF) with rear-seat observers (RSOs). The oblique-camera-count (OCC) approach, utilizing digital cameras on aircraft sides, proved to provide more reliable population estimates but incurs high manual processing costs. Addressing the urgent need for efficiency, the research explores whether a semi-automated deep learning (SADL) model coupled with OCC improves wildlife population estimates compared to the SRF-RSO method. The study area was the Comoé National Park, in Ivory Coast, spanning 11,488 km2 of savannas and open forests. It was surveyed following both SRF-RSO standards and OCC method. Key species included the elephant, western hartebeest, roan antelope, buffalo, kob, waterbuck and warthog. The deep learning model HerdNet, priorly pre-trained on images from Uganda, was incorporated in the SADL pipeline to process the 190,686 images. It involved three human verification steps to ensure quality of detections and to avoid overestimating counts. The entire pipeline aims to balance efficiency and human effort in wildlife population estimation. RSO and SADL-OCC approaches were compared using the Jolly II analysis and a verification of 200 random RSO observations. Jolly II analysis revealed SADL-OCC estimates significantly higher for small-sized species (kob, warthog) and comparable for other key species. Counting differences were mainly attributed to vegetation obstruction, RSO observations not found in the images, and suspected RSO counting errors. Human effort in the SADL-OCC approach totaled 111 h, representing a significant time savings compared to a fully manual interpretation. Introducing the SADL approach for aerial surveys in Comoé National Park enabled us to address the OCC's time-intensive image interpretation. Achieving a significant reduction in human workload, our method provided population estimates comparable to or better than SRF-RSO counts. Vegetation obstruction was a key factor explaining differences, highlighting the OCC method's limitation in vegetated areas. Method comparisons emphasized SADL-OCC's advantages in spotting isolated, small and static animals, reducing count variance between sample units. Despite limitations, the SADL-OCC approach offers transformative potential, suggesting a shift towards DL-assisted aerial surveys for increased efficiency and affordability, especially using microlight aircraft and drones in future wildlife monitoring initiatives.

Relation: https://api.elsevier.com/content/article/PII:S1574954124002218?httpAccept=text/xml; urn:issn:1574-9541; urn:issn:1878-0512

URL الوصول: https://orbi.uliege.be/handle/2268/319570

المؤلفون: Sosibo, Mbalenhle T., Ehlers Smith, David A., Ehlers Smith, Yvette C., Gumede, S. Thobeka, Ngcobo, Samukelisiwe P., Downs, Colleen T.^{Aff1, IDs42991022002435_cor6}

المصدر: Mammalian Biology: Zeitschrift für Säugetierkunde. 102(2):429-440

المؤلفون: Delplanque, Alexandre

المصدر: Forest Is Life Seminar, Gembloux, Belgium [BE], 07/04/2023

مصطلحات موضوعية: deep learning, aerial imagery, wildlife, remote sensing, herdnet, herds, african mammals, Engineering, computing & technology, Ingénierie, informatique & technologie

URL الوصول: https://orbi.uliege.be/handle/2268/304167

المؤلفون: Alexandre Delplanque, Samuel Foucher, Philippe Lejeune, Julie Linchant, Jérôme Théau

المصدر: Remote Sensing in Ecology and Conservation, Vol 8, Iss 2, Pp 166-179 (2022)

مصطلحات موضوعية: African mammals, CNNs, deep learning, multispecies, UAV, wildlife monitoring, Technology, Ecology, QH540-549.5

الوصف: Abstract Survey and monitoring of wildlife populations are among the key elements in nature conservation. The use of unmanned aerial vehicles and light aircrafts as aerial image acquisition systems is growing, as they are cheaper alternatives to traditional census methods. However, the manual localization and identification of species within imagery can be time‐consuming and complex. Object detection algorithms, based on convolutional neural networks (CNNs), have shown a good capacity for animal detection. Nevertheless, most of the work has focused on binary detection cases (animal vs. background). The main objective of this study is to compare three recent detection algorithms to detect and identify African mammal species based on high‐resolution aerial images. We evaluated the performance of three multi‐class CNN algorithms: Faster‐RCNN, Libra‐RCNN and RetinaNet. Six species were targeted: topis (Damaliscus lunatus jimela), buffalos (Syncerus caffer), elephants (Loxodonta africana), kobs (Kobus kob), warthogs (Phacochoerus africanus) and waterbucks (Kobus ellipsiprymnus). The best model was then applied to a case study using an independent dataset. The best model was the Libra‐RCNN, with the best mean average precision (0.80 ± 0.02), the lowest degree of interspecies confusion (3.5 ± 1.4%) and the lowest false positive per true positive ratio (1.7 ± 0.2) on the test set. This model was able to detect and correctly identify 73% of all individuals (1115), find 43 individuals of species other than those targeted and detect 84 missed individuals on our independent UAV dataset, with an average processing speed of 12 s/image. This model showed better detection performance than previous studies dealing with similar habitats. It was able to differentiate six animal species in nadir aerial images. Although limitations were observed with warthog identification and individual detection in herds, this model can save time and can perform precise surveys in open savanna.

وصف الملف: electronic resource

Relation: https://doaj.org/toc/2056-3485

URL الوصول: https://doaj.org/article/88ca6b128929482f83af51bf74d179cd

المؤلفون: Connie A. Rojas, Santiago Ramírez-Barahona, Kay E. Holekamp, Kevin R. Theis

المصدر: Animal Microbiome, Vol 3, Iss 1, Pp 1-18 (2021)

مصطلحات موضوعية: Herbivore gut microbiome, African mammals, Phylosymbiosis, Diet, 16S rRNA gene sequencing, Host ecology, Veterinary medicine, SF600-1100, Microbiology, QR1-502

الوصف: Abstract The gut microbiota is critical for host function. Among mammals, host phylogenetic relatedness and diet are strong drivers of gut microbiota structure, but one factor may be more influential than the other. Here, we used 16S rRNA gene sequencing to determine the relative contributions of host phylogeny and host diet in structuring the gut microbiotas of 11 herbivore species from 5 families living sympatrically in southwest Kenya. Herbivore species were classified as grazers, browsers, or mixed-feeders and dietary data (% C4 grasses in diet) were compiled from previously published sources. We found that herbivore gut microbiotas were highly species-specific, and that host taxonomy accounted for more variation in the gut microbiota (30%) than did host dietary guild (10%) or sample month (8%). Overall, similarity in the gut microbiota increased with host phylogenetic relatedness (r = 0.74) across the 11 species of herbivores, but among 7 closely related Bovid species, dietary %C4 grass values more strongly predicted gut microbiota structure (r = 0.64). Additionally, within bovids, host dietary guild explained more of the variation in the gut microbiota (17%) than did host species (12%). Lastly, while we found that the gut microbiotas of herbivores residing in southwest Kenya converge with those of distinct populations of conspecifics from central Kenya, fine-scale differences in the abundances of bacterial amplicon sequence variants (ASVs) between individuals from the two regions were also observed. Overall, our findings suggest that host phylogeny and taxonomy strongly structure the gut microbiota across broad host taxonomic scales, but these gut microbiotas can be further modified by host ecology (i.e., diet, geography), especially among closely related host species.

وصف الملف: electronic resource

Relation: https://doaj.org/toc/2524-4671

URL الوصول: https://doaj.org/article/cb7de3bd69d545348da0e1916b1b6e95

المؤلفون: Rojas, Connie A.^{Aff1, Aff2, Aff3}, Ramírez-Barahona, Santiago, Holekamp, Kay E.^{Aff1, Aff2, Aff3}, Theis, Kevin R.^{Aff3, Aff5}

المصدر: Animal Microbiome. 3(1)

المؤلفون: Delplanque, Alexandre, Foucher, Samuel, Lejeune, Philippe, Linchant, Julie, Théau, Jérôme

المصدر: Remote Sensing in Ecology and Conservation, 14 (2021-07)

مصطلحات موضوعية: African mammals, CNNs, deep learning, multispecies, UAV, wildlife monitoring, Life sciences, Agriculture & agronomy, Engineering, computing & technology, Sciences du vivant, Agriculture & agronomie, Ingénierie, informatique & technologie

الوصف: Survey and monitoring of wildlife populations are among the key elements in nature conservation. The use of unmanned aerial vehicles and light aircrafts as aerial image acquisition systems is growing, as they are cheaper alternatives to traditional census methods. However, the manual localization and identification of species within imagery can be time-consuming and complex. Object detection algorithms, based on convolutional neural networks (CNNs), have shown a good capacity for animal detection. Nevertheless, most of the work has focused on binary detection cases (animal vs. background). The main objective of this study is to compare three recent detection algorithms to detect and identify African mammal species based on high-resolution aerial images. We evaluated the performance of three multi-class CNN algorithms: Faster-RCNN, Libra-RCNN and RetinaNet. Six species were targeted: topis (Damaliscus lunatus jimela), buffalos (Syncerus caffer), elephants (Loxodonta africana), kobs (Kobus kob), warthogs (Phacochoerus africanus) and waterbucks (Kobus ellipsiprymnus). The best model was then applied to a case study using an independent dataset. The best model was the Libra-RCNN, with the best mean average precision (0.80 0.02), the lowest degree of interspecies confusion (3.5 1.4%) and the lowest false positive per true positive ratio (1.7 0.2) on the test set. This model was able to detect and correctly identify 73% of all individuals (1115), find 43 individuals of species other than those targeted and detect 84 missed individuals on our independent UAV dataset, with an average processing speed of 12 s/image. This model showed better detection performance than previous studies dealing with similar habitats. It was able to differentiate six animal species in nadir aerial images. Although limitations were observed with warthog identification and individual detection in herds, this model can save time and can perform precise surveys in open savanna.

Relation: https://doi.org/10.58119/ULG/MIRUU5; urn:issn:2056-3485

URL الوصول: https://orbi.uliege.be/handle/2268/262566

المؤلفون: Vrba, E. S.

المصدر: Philosophical Transactions: Biological Sciences, 2004 Feb . 359(1442), 285-293.

URL الوصول: https://www.jstor.org/stable/4142180

المؤلفون: Kirk, Jay.

مصطلحات موضوعية: American Museum of Natural History. Akeley Memorial Hall of African Mammals., Wild animal collectors -- United States -- Biography., Taxidermists -- United States -- Biography., Zoological specimens -- Collection and preservation -- Africa., Zoological specimens -- Collection and preservation., Taxidermists -- New York (State) -- Brockport.

Subject Person: Akeley, Carl Ethan, 1864-1926.

الوصف: An account of the life of the famed explorer and taxidermist assesses his influence on American views about natural-world conservation, covering his dangerous pursuits of wildlife for his dioramas.
Akeley studied taxidemry in Brockport, NY, with George Guelf (many of whose glass slide plates are in the College Archives at Drake Memorial Library, The College at Brockprt).

المؤلفون: Frizzelle, Nikita R

المصدر: Electronic Thesis and Dissertation Repository

مصطلحات موضوعية: African mammals, hunting, parasitic diseases, antipredator behaviour, fear, experimental manipulation, human "super-predator", Behavior and Ethology

الوصف: Humans’ exploitive killing of virtually every mammal species globally may result in a perception of humans as feared, ultra-lethal predators. In Africa, mammals are central to the continent’s tourism industry; however, it is largely unknown whether African mammals fear the presence of tourists. Firstly, I aimed to review how the presence of humans on the landscape affects African mammal behaviour. Of 31 studies, most authors reported that humans alter mammal behaviour in a manner that may negatively impact survival. To test if a fear of humans can pervade communities, I simulated the presence of humans, hunting, lions, and birds using an Automated Behavioural Response system. I recorded fleeing responses of 26 South African mammal species and found that the community fled most to human voices, especially when heard where hunting occurs. My results demonstrate that human presence induces a greater community-wide fear response than the presence of their natural predator.

وصف الملف: application/pdf

URL الوصول: https://explore.openaire.eu/search/publication?articleId=od______1548::0750c02954eb47a12e74a58cdc3aca3d
https://ir.lib.uwo.ca/context/etd/article/10946/viewcontent/MSc_thesis_NFrizzelle_21December2021_forfinalsubmission.pdf