气候变化领域集成服务门户(CCPortal): Evaluating the performance of semiautomated photographic identification programs for leopard seals

CCPortal

DOI	10.1002/wsb.1520
	Evaluating the performance of semiautomated photographic identification programs for leopard seals
	Grabham, Alexander A.; van der Linde, Krista; Nelson, Ximena J.
发表日期	2024
ISSN	2328-5540
英文摘要	The photographic identification (photo-ID) of individual animals can be time-consuming and erroneous. Recent efforts to collect photographs of leopard seals (Hydrurga leptonyx) from across their range have necessitated the technological streamlining of photo-ID. We constructed a dataset containing 595 photographs of the head and body of individuals recorded in New Zealand between 2008 and 2022 to test the performance of semiautomated 3 photo-ID programs: HotSpotter, Interactive Individual Identification System's Pattern+ (I3S), and Wild-ID. We classified attributes of photographs (e.g., quality) and individuals (i.e., pelage patterns) to assess their effect on performance. We compared performance using Top20 and Top1 Accuracy, defined as the proportion of test photographs where the highest ranked correct identity was in the top 20 and top 1, respectively, matched reference photographs. HotSpotter outperformed I3S and Wild-ID in both Top20 and Top1 Accuracy of most assessed attributes. Maximizing HotSpotter's performance may be achieved through several methods, including increasing the number and variety of photographs of individuals in the dataset. HotSpotter will likely perform better with photographs without obstructions (e.g., debris from beaches), such as on the pack ice of their primary Antarctic range. We highlight the viability of HotSpotter in assisting the photo-ID of leopard seals, and more broadly, other species with similar markings. The movement and distribution of leopard seals in relation to climate change can be examined in a more timely and cost-effective manner using technology. We evaluated the performance of three semiautomated photographic identification programs, HotSpotter, Interactive Individual Identification System's Pattern+ (I3S), and Wild-ID, with leopard seal photographs. Attributes of photographs and individuals were assessed to determine program performance with other datasets. image
英文关键词	Hydrurga leptonyx; Individual identification; New Zealand; performance; photo-ID; pinniped; program; software
语种	英语
WOS研究方向	Biodiversity & Conservation
WOS类目	Biodiversity Conservation
WOS记录号	WOS:001224693700001
来源期刊	WILDLIFE SOCIETY BULLETIN
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/303054
作者单位	University of Canterbury
推荐引用方式 GB/T 7714	Grabham, Alexander A.,van der Linde, Krista,Nelson, Ximena J.. Evaluating the performance of semiautomated photographic identification programs for leopard seals[J],2024.
APA	Grabham, Alexander A.,van der Linde, Krista,&Nelson, Ximena J..(2024).Evaluating the performance of semiautomated photographic identification programs for leopard seals.WILDLIFE SOCIETY BULLETIN.
MLA	Grabham, Alexander A.,et al."Evaluating the performance of semiautomated photographic identification programs for leopard seals".WILDLIFE SOCIETY BULLETIN (2024).