|
Bohnett, E., Faryabi, S. P., Lewison, R., An, L., Bian, X., Rajabi, A. M., Jahed, N., Rooyesh, H., Mills, E., Ramos, S., Mesnildrey, N., Perez, C. M. S., Taylor, J., Terentyev, V., Ostrowski, S. (2023). Human expertise combined with artificial intelligence improves performance of snow leopard camera trap studies. Global Ecology & Conservation, 41(e02350), 1–13.
Abstract: Camera trapping is the most widely used data collection method for estimating snow leopard (Panthera uncia) abundance; however, the accuracy of this method is limited by human observer errors from misclassifying individuals in camera trap images. We evaluated the extent Whiskerbook (www.whiskerbook.org), an artificial intelligence (AI) software, could reduce this error rate and enhance the accuracy of capture-recapture abundance estimates. Using 439 images of 34 captive snow leopard individuals, classification was performed by five observers with prior experience in individual snow leopard ID (“experts”) and five observers with no such experience (“novices”). The “expert” observers classified 35 out of 34 snow leopard individuals, on average erroneously splitting one individual into two, thus resulting in a higher number than true individuals. The success rate of experts was 90 %, with less than a 3 % error in estimating the population size in capture-recapture modeling. However, the “novice” observers successfully matched 71 % of encounters, recognizing 25 out of 34 individuals, underestimating the population by 25 %. It was found that expert observers significantly outperformed novice observers, making statistically fewer errors (Mann Whitney U test P = 0.01) and finding the true number of individuals (P = 0.01). These differences were contrasted with a previous study by Johansson et al. 2020, using the same subset of 16 individuals from European zoos. With the help of AI and the Whiskerbook platform, “experts” were able to match 87 % of encounters and identify 15 out of 16 individuals, with modeled estimates of 16 ± 1 individuals. In contrast, “novices” were 63 % accurate in matching encounters and identified 12 out of 16 individuals, modeling 12 ± 1 individuals that underestimated the population size by 12 %. When comparing the performance of observers using AI and the Whiskerbook platform to observers performing the tasks manually, we found that observers using Whiskerbook made significantly fewer errors in splitting one individual into two (P = 0.04). However, there were also a significantly higher number of combination errors, where two individuals were combined into one (P = 0.01). Specifically, combination errors were found to be made by “novices” (P = 0.04). Although AI benefited both expert and novice observers, expert observers outperformed novices. Our results suggest that AI effectively reduced the misclassification of individual snow leopards in camera trap studies, improving abundance estimates. However, even with AI support, expert observers were needed to obtain the most accurate estimates.
|
|
|
Bohnett, E., Holmberg, J., Faryabi, S. P., An, L., Ahmad, B., Rashid, W., Ostrowski, S. (2023). Comparison of two individual identification algorithms for snow leopards (Panthera uncia) after automated detection. Ecological Informatics, 77(102214), 1–14.
Abstract: Photo-identification of individual snow leopards (Panthera uncia) is the primary data source for density estimation via capture-recapture statistical methods. To identify individual snow leopards in camera trap imagery, it is necessary to match individuals from a large number of images from multiple cameras and historical catalogues, which is both time-consuming and costly. The camouflaged snow leopards also make it difficult for machine learning to classify photos, as they blend in so well with the surrounding mountain environment, rendering applicable software solutions unavailable for the species. To potentially make snow leopard individual identification available via an artificial intelligence (AI) software interface, we first trained and evaluated image classification techniques for a convolutional neural network, pose invariant embeddings (PIE) (a triplet loss network), and compared the accuracy of PIE to that of the HotSpotter algorithm (a SIFT-based algorithm). Data were acquired from a curated library of free-ranging snow leopards taken in Afghanistan between 2012 and 2019 and from captive animals in zoos in Finland, Sweden, Germany, and the United States. We discovered several flaws in the initial PIE model, such as a small amount of background matching, that was addressed, albeit likely not fixed, using background subtraction (BGS) and left-right mirroring (LR) techniques which demonstrated reasonable accuracy (Rank 1: 74% Rank-5: 92%) comparable to the Hotspotter results (Rank 1: 74% Rank 2: 84%)The PIE BGS LR model, in conjunction with Hotspotter, yielded the following results: Rank-1: 85%, Rank-5: 95%, Rank-20: 99%. In general, our findings indicate that PIE BGS LR, in conjunction with HotSpotter, can classify snow leopards more accurately than using either algorithm alone.
|
|
|
Bower, J. N. (1980). For some endangered species, captive breeding programs are their last chance for life. National Parks and Conservation Magazine, (June), 16–19.
|
|
|
Bower, J. N. (1983). Shy, elusive, struggling to survive: the snow leopard. The Explorer, , 9–11.
|
|
|
Bowling, B. (2004). The Legal Status of Snow Leopards in Afghanistan. United Nations Environment Programme.
|
|
|
Braden, K. (1988). Snow leopard conservation in the USSR. Snow Line, Fall, 2.
|
|
|
Brem A.E. (1992). Irbis, or snow leopard (Felis uncia) (Vol. Vol.1. Mammals.).
Abstract: Snow leopard is met in the mountains of Turkistan, Altai, Bukhara, Pamir, Kashmir, and Tibet, and probably in South-East Siberia and along Sungari. In 1871, two animals were living in the Moscow Zoo Garden.
|
|
|
Broder, J., MacFadden, A., Cosens, L., Rosenstein, D., & Harrison, T. (2008). Use of Positive Reinforcement Conditioning to Monitor Pregnancy in an Unanesthetized Snow Leopard
(Uncia uncia) via Transabdominal Ultrasound (Vol. 27).
Abstract: Closely monitoring snow leopard (Uncia uncia) fetal developments via transabdominal ultrasound, with minimal stress to the animal, was the goal of this project. The staff at Potter Park Zoo has used the principles of habituation, desensitization, and positive reinforcement to train a female snow leopard (U. uncia). Ultrasound examinations were preformed on an unanesthetized feline at 63 and 84 days. The animal remained calm and compliant throughout both procedures. Fetuses were observed and measured on both occasions. The absence of anesthesia eliminated components of psychologic and physiologic stress associated with sedation. This was the first recorded instance of transabdominal ultrasound being carried out on an unanesthetized snow leopard. It documents the feasibility of detecting pregnancy and monitoring fetal development via ultrasound.
|
|
|
Brown, J. L., Wasser, S. K., Wildt, D. E., & Graham, L. H. (1994). Steroid Metabolism and the Effectiveness of Fecal Assays for Assessing Reproductive Status in Felids. Biology of Reproduction, 50(suppl 1), 185.
|
|
|
Burgelo T.B. (1986). Brief information of snow leopard.
Abstract: This article describes the encounters with snow leopard and their traces in various areas of Kazakhstan. In the Aksu Djabagly nature reserve, population of snow leopard does not exceed 10-12 animals. There were found remains of moral, argali, ibex, small birds, red-tailed marmot, hare (Lepus talai), mouse rodents and plants. One encounter with snow leopard is known to have occurred in the Greater Almaty Canyon in 1971-1981. There are no less than 25 snow leopards in the Jungar Ala-Tau. Snow leopard was found in the Aksu river valley, ridge Saur, and South Altai. The following number of snow leopards was kept in Kazakhstan's zoos, as of January 1, 1984: two males in Alma-Ata, one female in Chimkent. In 1976, one cub was born in the Alma-Ata zoo.
|
|