Identifying individual jaguars from camera-trap images using the HotSpotter program

IF 0.8 4区生物学 Q3 ZOOLOGY

Mammalia Pub Date : 2023-10-16 DOI:10.1515/mammalia-2023-0071

Øystein Wiig, Karollyna da Silva Teixeira, Leonardo Sena, Halícia Celeste Santos de Oliveira, Ana Cristina Mendes-Oliveira

引用次数: 0

Abstract

Abstract We identified individual jaguars from a database of camera-trap images collected in the Eastern Amazonian rainforest using the artificial intelligence software HotSpotter. We identified individuals from 131 of 217 images. Twenty-five different individuals were identified based on images of the left side. We compared our results with the results from an undergraduate study that manually identified 18 jaguar individuals from 53 images also used in the present study. One of the 18 individuals was found to be misclassified based on HotSpotter. We found HotSpotter to be useful in identifying individual jaguars in our study area.

查看原文本刊更多论文

使用HotSpotter程序从相机陷阱图像中识别单个美洲虎

我们利用人工智能软件HotSpotter从东亚马逊雨林收集的相机陷阱图像数据库中识别出美洲虎个体。我们从217张图片中的131张中识别出了个体。根据左脑的图像识别出了25个不同的个体。我们将我们的结果与一项本科研究的结果进行了比较，该研究从53张图像中手动识别了18只美洲虎个体，也用于本研究。在这18个人中，有一人被发现是根据HotSpotter错误分类的。我们发现HotSpotter在识别我们研究区域的美洲虎个体方面很有用。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Mammalia 生物-动物学

CiteScore

2.20

自引率

10.00%

发文量

审稿时长

6-12 weeks

期刊介绍： Mammalia is an international, multidisciplinary, bimonthly journal devoted to the inventory, analysis and interpretation of mammalian diversity. It publishes original results on all aspects of the systematics and biology of mammals with a strong focus on ecology, including biodiversity analyses, distribution habitats, diet, predator-prey relationships, competition, community analyses and conservation of mammals. The journal also accepts submissions on sub-fossil or recently extinct mammals.